Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "q_proj",
     "k_proj",
-    "down_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj"
+    "down_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 sha256:28d818039cbf8e1612d5cb1306c0c9eb439cd19b8a3cf107aba686263f3a10f3
+oid sha256:e32750df981a4ce26abc6cf68283301bb1690a4d7ef093fababe48a991416d39
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26404cd7cf4589950b21359f9d386d0347e7ef5b27e15bcc3395c3898f572d0f
+oid sha256:c4febca87fdd5a91d45db60971a84df06ab6cd95003f9aa213c8f2366f64114c
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50cc0a3e92dca42053d2ef622567a9f710a3429c2adfbbce542167578fceae6
+oid sha256:7550804b36e779534bc6ad3f8eb519f03ede146db31006d3a58ef3bed8b2fb40
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0140d392838184af026303533cb58f2174562eda6a4742ff6da5b3d95df2f9ec
+oid sha256:e7e6b5ed1c31a47db9aa144dffea45f466b2da22de0292e0863e50c62e6ebc1c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,114 +1,93 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.75,
-  "eval_steps": 3,
-  "global_step": 9,
+  "epoch": 1.0,
+  "eval_steps": 2,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.08333333333333333,
+      "epoch": 0.16666666666666666,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.4924,
+      "loss": 1.3997,
       "step": 1
     },
     {
-      "epoch": 0.08333333333333333,
-      "eval_loss": 1.4975985288619995,
-      "eval_runtime": 0.1911,
-      "eval_samples_per_second": 15.701,
-      "eval_steps_per_second": 15.701,
+      "epoch": 0.16666666666666666,
+      "eval_loss": 1.4973297119140625,
+      "eval_runtime": 0.2886,
+      "eval_samples_per_second": 10.395,
+      "eval_steps_per_second": 6.93,
       "step": 1
     },
     {
-      "epoch": 0.16666666666666666,
-      "grad_norm": 5.183752536773682,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 5.478867530822754,
       "learning_rate": 2e-05,
-      "loss": 1.3074,
+      "loss": 1.4535,
       "step": 2
     },
     {
-      "epoch": 0.25,
-      "grad_norm": 6.239664077758789,
-      "learning_rate": 4e-05,
-      "loss": 1.5739,
-      "step": 3
+      "epoch": 0.3333333333333333,
+      "eval_loss": 1.4973297119140625,
+      "eval_runtime": 0.284,
+      "eval_samples_per_second": 10.565,
+      "eval_steps_per_second": 7.043,
+      "step": 2
     },
     {
-      "epoch": 0.25,
-      "eval_loss": 1.4466005563735962,
-      "eval_runtime": 0.211,
-      "eval_samples_per_second": 14.216,
-      "eval_steps_per_second": 14.216,
+      "epoch": 0.5,
+      "grad_norm": 5.20695686340332,
+      "learning_rate": 4e-05,
+      "loss": 1.5303,
       "step": 3
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 5.012392044067383,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.481665134429932,
       "learning_rate": 6e-05,
-      "loss": 1.2793,
+      "loss": 1.394,
       "step": 4
     },
     {
-      "epoch": 0.4166666666666667,
-      "grad_norm": 3.691774845123291,
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.2689329385757446,
+      "eval_runtime": 0.3021,
+      "eval_samples_per_second": 9.93,
+      "eval_steps_per_second": 6.62,
+      "step": 4
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 3.2430155277252197,
       "learning_rate": 8e-05,
-      "loss": 1.3057,
+      "loss": 1.2373,
       "step": 5
     },
     {
-      "epoch": 0.5,
-      "grad_norm": 3.0195882320404053,
+      "epoch": 1.0,
+      "grad_norm": 2.6539690494537354,
       "learning_rate": 0.0001,
-      "loss": 1.0885,
+      "loss": 1.0206,
       "step": 6
     },
     {
-      "epoch": 0.5,
-      "eval_loss": 0.8231927752494812,
-      "eval_runtime": 0.2024,
-      "eval_samples_per_second": 14.826,
-      "eval_steps_per_second": 14.826,
+      "epoch": 1.0,
+      "eval_loss": 0.7840422987937927,
+      "eval_runtime": 0.3266,
+      "eval_samples_per_second": 9.185,
+      "eval_steps_per_second": 6.123,
       "step": 6
-    },
-    {
-      "epoch": 0.5833333333333334,
-      "grad_norm": 2.5046184062957764,
-      "learning_rate": 0.00012,
-      "loss": 0.8365,
-      "step": 7
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 2.7154762744903564,
-      "learning_rate": 0.00014,
-      "loss": 0.5475,
-      "step": 8
-    },
-    {
-      "epoch": 0.75,
-      "grad_norm": 2.8666529655456543,
-      "learning_rate": 0.00016,
-      "loss": 0.2414,
-      "step": 9
-    },
-    {
-      "epoch": 0.75,
-      "eval_loss": 0.049252700060606,
-      "eval_runtime": 0.2077,
-      "eval_samples_per_second": 14.444,
-      "eval_steps_per_second": 14.444,
-      "step": 9
     }
   ],
   "logging_steps": 1,
-  "max_steps": 10,
+  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 3,
+  "save_steps": 2,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -116,12 +95,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1664607823331328.0,
+  "total_flos": 2219477097775104.0,
   "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:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
+oid sha256:74dcf4a29346d06a18985986c93532599870827345febcfc1739afefe0e2e2b9
 size 6776