Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "down_proj",
     "gate_proj",
+    "o_proj",
     "up_proj",
     "v_proj",
     "k_proj",
-    "down_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2319a6703db5a487f79bb5e5b841b20cff97957a2b414d0343a5f419b6aeec6
+oid sha256:bf2de42c66ae50cfea38041b439f4b531ff69d52594c4cc92575e92e06a4e3f1
 size 244554

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84060bcb32bd44939e90e66e82b623d70d5883ccf73445738807437d4680bbd7
+oid sha256:74aafd80eb160e138d50a2e12cd2be0a0f053ac6c5e23cbd795285ea4cfeb232
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba5fca67effb4371b474b4c0b5c873e43e184ac6c24c83481e8d54e3376773a
+oid sha256:0492bc9242d5003ccf8609e95fbfd8044f4304f992894db98e3ee6048eb409af
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced912156d9c7727370ff7b3a64a49d4c1365c17fc5506c09158671667b90801
+oid sha256:6ff0fad10893c30bb2c25104e2a97752d4a51a326b5697000e5fa724d0e9d106
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0742e67cc3c0d4be3fdbc3b26531d1f9ce6faccb6a0969c2763b7b51a147aeb2
+oid sha256:e018329612d2cf191139e7718bbe39100d6a1981e1838e00bcb59a5677393993
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6514657980456026,
+  "epoch": 1.3029315960912053,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.026058631921824105,
       "eval_loss": NaN,
-      "eval_runtime": 0.5893,
-      "eval_samples_per_second": 439.496,
-      "eval_steps_per_second": 55.998,
+      "eval_runtime": 0.2562,
+      "eval_samples_per_second": 1010.966,
+      "eval_steps_per_second": 128.81,
       "step": 1
     },
     {
@@ -194,10 +194,193 @@
     {
       "epoch": 0.6514657980456026,
       "eval_loss": NaN,
-      "eval_runtime": 0.4126,
-      "eval_samples_per_second": 627.756,
-      "eval_steps_per_second": 79.984,
+      "eval_runtime": 0.2552,
+      "eval_samples_per_second": 1014.721,
+      "eval_steps_per_second": 129.289,
       "step": 25
+    },
+    {
+      "epoch": 0.6775244299674267,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.7035830618892508,
+      "grad_norm": NaN,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.7296416938110749,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.755700325732899,
+      "grad_norm": NaN,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.7817589576547231,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.8078175895765473,
+      "grad_norm": NaN,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.8338762214983714,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.8599348534201955,
+      "grad_norm": NaN,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.8859934853420195,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.9120521172638436,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.9381107491856677,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.9641693811074918,
+      "grad_norm": NaN,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.990228013029316,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.01628664495114,
+      "grad_norm": NaN,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.0423452768729642,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0684039087947883,
+      "grad_norm": NaN,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.0944625407166124,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.1205211726384365,
+      "grad_norm": NaN,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.1465798045602607,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.1726384364820848,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.1986970684039089,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.224755700325733,
+      "grad_norm": NaN,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.2508143322475571,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.2768729641693812,
+      "grad_norm": NaN,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5208,
+      "eval_samples_per_second": 170.304,
+      "eval_steps_per_second": 21.699,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 41877189427200.0,
+  "total_flos": 83754378854400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9ce3dede1171fbae96fc9e469488048390a8e9e48e1e8b2b43082992111f35
+oid sha256:0290b9e0572c0442e2f3c5bb8154917b3c206aa2dee90567c3ae5345037c31cd
 size 6776