Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d62c59a22d074ea25f4d3cf45ad91c2015d68ff6a3b1fe187695cf818751fdd
+oid sha256:68f487aa222d26357d3b760e9a17f69a08eedbd42c11631c61da3f7ab345eaa8
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89657f9d55a8fb888a19b5830288050f2aea41864ec29c8ad8c276fe984fc1ad
+oid sha256:ddd06a1d51d594964d2231d0a9f1dcd7ce979116db8da9b5de5ff823411dcb44
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b42c575c29d091a3169a5b5e4dee4ed6423326b999205a7ebc24343c755d173
+oid sha256:1f8bc6fa9761b34169cf09009a689be0421c610ccd837675a87112c385c8cad5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003361127270376834,
+  "epoch": 0.004309137526124146,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,9 +11,9 @@
     {
       "epoch": 8.618275052248293e-05,
       "eval_loss": NaN,
-      "eval_runtime": 331.7922,
-      "eval_samples_per_second": 14.726,
-      "eval_steps_per_second": 7.363,
+      "eval_runtime": 336.0585,
+      "eval_samples_per_second": 14.539,
+      "eval_steps_per_second": 7.27,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.0008618275052248292,
       "eval_loss": NaN,
-      "eval_runtime": 331.9842,
-      "eval_samples_per_second": 14.718,
-      "eval_steps_per_second": 7.359,
+      "eval_runtime": 335.5914,
+      "eval_samples_per_second": 14.559,
+      "eval_steps_per_second": 7.28,
       "step": 10
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.0017236550104496584,
       "eval_loss": NaN,
-      "eval_runtime": 331.1945,
-      "eval_samples_per_second": 14.753,
-      "eval_steps_per_second": 7.376,
+      "eval_runtime": 335.6421,
+      "eval_samples_per_second": 14.557,
+      "eval_steps_per_second": 7.279,
       "step": 20
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.0025854825156744875,
       "eval_loss": NaN,
-      "eval_runtime": 330.4337,
-      "eval_samples_per_second": 14.787,
-      "eval_steps_per_second": 7.393,
+      "eval_runtime": 335.398,
+      "eval_samples_per_second": 14.568,
+      "eval_steps_per_second": 7.284,
       "step": 30
     },
     {
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.003447310020899317,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.003447310020899317,
+      "eval_loss": NaN,
+      "eval_runtime": 335.6166,
+      "eval_samples_per_second": 14.558,
+      "eval_steps_per_second": 7.279,
+      "step": 40
+    },
+    {
+      "epoch": 0.0038782237735117317,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.004309137526124146,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.004309137526124146,
+      "eval_loss": NaN,
+      "eval_runtime": 335.7403,
+      "eval_samples_per_second": 14.553,
+      "eval_steps_per_second": 7.276,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7754730405101568.0,
+  "total_flos": 1.0107289067323392e+16,
   "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:fa1d37cf89fbf818b70abdb7b8d6f4e2e14ae744a7c9847899987fedf464b73f
+oid sha256:25fd71fe8415b64b1f441eb970a98b37a04133c8317c80879bf54aa07922811c
 size 6776