Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
     "q_proj",
-    "up_proj",
+    "o_proj",
     "gate_proj",
-    "down_proj",
-    "o_proj"
+    "v_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 sha256:586766f80b818da33cc910ae62f532be1be0faeffc306263f4d65ffdde9ee426
+oid sha256:ac4e49830ca4084ef96f5c95d7ee075a79d349858c85e07cc39702093eaa3455
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b55fdeaa972ee613d6eefe443c0ae661e274b479aab76b6e37ff6de048dfd3
+oid sha256:2671111e7f8b7b54f65ad73c945053eefc3d6789e802b6ccdc864b5ab113e011
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
+oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008097165991902834,
+  "epoch": 0.0024291497975708503,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 4.8993353843688965,
+      "grad_norm": 5.536149024963379,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 16.8151,
-      "eval_samples_per_second": 15.522,
-      "eval_steps_per_second": 15.522,
+      "eval_runtime": 46.298,
+      "eval_samples_per_second": 5.637,
+      "eval_steps_per_second": 5.637,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.014788627624512,
+      "grad_norm": 5.57291841506958,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,81 +34,16 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5658,
+      "loss": 17.5653,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.011764526367188,
-      "eval_runtime": 16.886,
-      "eval_samples_per_second": 15.457,
-      "eval_steps_per_second": 15.457,
+      "eval_loss": 16.010469436645508,
+      "eval_runtime": 48.2421,
+      "eval_samples_per_second": 5.41,
+      "eval_steps_per_second": 5.41,
       "step": 3
-    },
-    {
-      "epoch": 0.0032388663967611335,
-      "grad_norm": 4.659067153930664,
-      "learning_rate": 6e-05,
-      "loss": 15.4637,
-      "step": 4
-    },
-    {
-      "epoch": 0.004048582995951417,
-      "grad_norm": 6.414226531982422,
-      "learning_rate": 8e-05,
-      "loss": 14.5141,
-      "step": 5
-    },
-    {
-      "epoch": 0.004858299595141701,
-      "grad_norm": 6.8862433433532715,
-      "learning_rate": 0.0001,
-      "loss": 14.5333,
-      "step": 6
-    },
-    {
-      "epoch": 0.004858299595141701,
-      "eval_loss": 15.220080375671387,
-      "eval_runtime": 17.3934,
-      "eval_samples_per_second": 15.006,
-      "eval_steps_per_second": 15.006,
-      "step": 6
-    },
-    {
-      "epoch": 0.005668016194331984,
-      "grad_norm": 7.203052997589111,
-      "learning_rate": 0.00012,
-      "loss": 16.3026,
-      "step": 7
-    },
-    {
-      "epoch": 0.006477732793522267,
-      "grad_norm": 8.219391822814941,
-      "learning_rate": 0.00014,
-      "loss": 13.8997,
-      "step": 8
-    },
-    {
-      "epoch": 0.0072874493927125505,
-      "grad_norm": 11.033364295959473,
-      "learning_rate": 0.00016,
-      "loss": 13.1099,
-      "step": 9
-    },
-    {
-      "epoch": 0.0072874493927125505,
-      "eval_loss": 12.117241859436035,
-      "eval_runtime": 17.9248,
-      "eval_samples_per_second": 14.561,
-      "eval_steps_per_second": 14.561,
-      "step": 9
-    },
-    {
-      "epoch": 0.008097165991902834,
-      "grad_norm": 13.987093925476074,
-      "learning_rate": 0.00018,
-      "loss": 12.2937,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1643164226027520.0,
+  "total_flos": 492949267808256.0,
   "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:a45ccf46e14ed35216c4e7a3c80c48f1548a7a4ee495cb102e2d1263e0be3188
+oid sha256:cc7eb56965fd55276c944caeebbd855891392f90553ede8609b47d5de737c680
 size 6776