Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "o_proj",
-    "down_proj",
     "v_proj",
+    "down_proj",
     "k_proj",
-    "q_proj",
-    "gate_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578e4a116d737b4e48d7aaaa16fe1335d55d16873df6f110e9f8a01913473ae8
+oid sha256:24261f18d4381a1bc677301241cc8b1ecbf6164e643e29227d41992d11a1fa07
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ec9c6298662bd0a910669e1d24cdf60f12d9db0a83a40568be82ede0684acb
+oid sha256:522f1995fc39e52cb305b10202e2bb9708dd632162c39cf98219fef97bcac87c
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
+oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00045428733674048835,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005905735377626349,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00045428733674048835,
       "eval_loss": 2.3526980876922607,
-      "eval_runtime": 49.7875,
-      "eval_samples_per_second": 18.619,
-      "eval_steps_per_second": 9.32,
+      "eval_runtime": 48.7648,
+      "eval_samples_per_second": 19.01,
+      "eval_steps_per_second": 9.515,
       "step": 1
+    },
+    {
+      "epoch": 0.002271436683702442,
+      "grad_norm": 6.649918079376221,
+      "learning_rate": 5e-05,
+      "loss": 2.2383,
+      "step": 5
+    },
+    {
+      "epoch": 0.004542873367404884,
+      "grad_norm": 3.9040491580963135,
+      "learning_rate": 0.0001,
+      "loss": 1.5065,
+      "step": 10
+    },
+    {
+      "epoch": 0.004542873367404884,
+      "eval_loss": 0.6507410407066345,
+      "eval_runtime": 48.9057,
+      "eval_samples_per_second": 18.955,
+      "eval_steps_per_second": 9.488,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 50009733070848.0,
+  "total_flos": 650126529921024.0,
   "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 sha256:79bebe3ab60c99e46aa91057881cd074c3ad69844718e24deee56e265ba2fd34
+oid sha256:620b62d3b1208e48ab7fe349f2a66017c17b245c9c9be733bb4b8ece19405b01
 size 6776