Training in progress, step 8, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
+    "v_proj",
     "up_proj",
-    "q_proj",
     "down_proj",
-    "v_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj",
+    "o_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 sha256:5a32d389a9b3f151214705183b0c282d77e669cd08af614fc7aba8ca778c1316
+oid sha256:8e01b0be7e155c46dcef4dc868716ea0b738a9c2e15c9d502353b4b10de17f86
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d7f55e40ffb7db072fd318cd8fd23188dd0b8c092620f93ecb0f3287cd9fdc
-size 85723284
+oid sha256:ea3b2511b29d46ea22d9653846690fb23fa086dc65a7e51a9d9b87f6726b6ed8
+size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46e88b4c6d353657e53552d7e0de44c36fe47ff4c4a5c23dafe2255812f99e9
+oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,56 +1,92 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033769523005487546,
+  "epoch": 0.0033773087071240107,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0008442380751371887,
-      "grad_norm": NaN,
+      "epoch": 0.00042216358839050134,
+      "grad_norm": 6.515402317047119,
       "learning_rate": 2e-05,
-      "loss": 0.0,
+      "loss": 6.2351,
       "step": 1
     },
     {
-      "epoch": 0.0008442380751371887,
-      "eval_loss": NaN,
-      "eval_runtime": 40.4739,
-      "eval_samples_per_second": 12.329,
-      "eval_steps_per_second": 6.177,
+      "epoch": 0.00042216358839050134,
+      "eval_loss": 7.163845539093018,
+      "eval_runtime": 59.6773,
+      "eval_samples_per_second": 8.362,
+      "eval_steps_per_second": 8.362,
       "step": 1
     },
     {
-      "epoch": 0.0016884761502743773,
-      "grad_norm": NaN,
+      "epoch": 0.0008443271767810027,
+      "grad_norm": 6.853526592254639,
       "learning_rate": 4e-05,
-      "loss": 0.0,
+      "loss": 6.2997,
       "step": 2
     },
     {
-      "epoch": 0.002532714225411566,
-      "grad_norm": NaN,
+      "epoch": 0.001266490765171504,
+      "grad_norm": 7.778280735015869,
       "learning_rate": 6e-05,
-      "loss": 0.0,
+      "loss": 7.021,
       "step": 3
     },
     {
-      "epoch": 0.0033769523005487546,
-      "grad_norm": NaN,
+      "epoch": 0.0016886543535620053,
+      "grad_norm": 8.638328552246094,
       "learning_rate": 8e-05,
-      "loss": 0.0,
+      "loss": 7.51,
       "step": 4
     },
     {
-      "epoch": 0.0033769523005487546,
-      "eval_loss": NaN,
-      "eval_runtime": 39.7116,
-      "eval_samples_per_second": 12.566,
-      "eval_steps_per_second": 6.295,
+      "epoch": 0.0016886543535620053,
+      "eval_loss": 6.921504974365234,
+      "eval_runtime": 59.6612,
+      "eval_samples_per_second": 8.364,
+      "eval_steps_per_second": 8.364,
       "step": 4
+    },
+    {
+      "epoch": 0.0021108179419525065,
+      "grad_norm": 8.384474754333496,
+      "learning_rate": 0.0001,
+      "loss": 6.6173,
+      "step": 5
+    },
+    {
+      "epoch": 0.002532981530343008,
+      "grad_norm": 6.948892116546631,
+      "learning_rate": 0.00012,
+      "loss": 5.3785,
+      "step": 6
+    },
+    {
+      "epoch": 0.0029551451187335093,
+      "grad_norm": 7.122462749481201,
+      "learning_rate": 0.00014,
+      "loss": 5.7491,
+      "step": 7
+    },
+    {
+      "epoch": 0.0033773087071240107,
+      "grad_norm": 8.084318161010742,
+      "learning_rate": 0.00016,
+      "loss": 4.7822,
+      "step": 8
+    },
+    {
+      "epoch": 0.0033773087071240107,
+      "eval_loss": 4.463127613067627,
+      "eval_runtime": 59.3591,
+      "eval_samples_per_second": 8.406,
+      "eval_steps_per_second": 8.406,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,8 +106,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1483774567120896.0,
-  "train_batch_size": 2,
+  "total_flos": 2967549134241792.0,
+  "train_batch_size": 1,
   "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:dfe6c9b320916ba73b5ecd7d507cc1843cb46082183e02f95c9c663f599d80e6
+oid sha256:3a3833977106fac48f5d71407b1a01067110c5fbf699342151524802ba318de1
 size 6776