Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
     "o_proj",
     "q_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj",
     "down_proj",
     "v_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e32750df981a4ce26abc6cf68283301bb1690a4d7ef093fababe48a991416d39
+oid sha256:5b37c3c3688bef73b576a3530942694ccb9f025c5852ff9698238ba1124acec3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4febca87fdd5a91d45db60971a84df06ab6cd95003f9aa213c8f2366f64114c
+oid sha256:9857d29be73ca23bbf30f9c1582a975f9e8c9413eaf40fd4594f3094f2f38238
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea4a6c63434c27a483922b729f3295cf32c5e237d07366009f63d639620f157
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/trainer_state.json

@@ -1,93 +1,85 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 2,
+  "epoch": 0.5,
+  "eval_steps": 3,
   "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.16666666666666666,
+      "epoch": 0.08333333333333333,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.3997,
+      "loss": 1.4927,
       "step": 1
     },
     {
-      "epoch": 0.16666666666666666,
-      "eval_loss": 1.4973297119140625,
-      "eval_runtime": 0.2886,
-      "eval_samples_per_second": 10.395,
-      "eval_steps_per_second": 6.93,
+      "epoch": 0.08333333333333333,
+      "eval_loss": 1.4977792501449585,
+      "eval_runtime": 0.3019,
+      "eval_samples_per_second": 9.937,
+      "eval_steps_per_second": 9.937,
       "step": 1
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 5.478867530822754,
+      "epoch": 0.16666666666666666,
+      "grad_norm": 4.949731349945068,
       "learning_rate": 2e-05,
-      "loss": 1.4535,
-      "step": 2
-    },
-    {
-      "epoch": 0.3333333333333333,
-      "eval_loss": 1.4973297119140625,
-      "eval_runtime": 0.284,
-      "eval_samples_per_second": 10.565,
-      "eval_steps_per_second": 7.043,
+      "loss": 1.307,
       "step": 2
     },
     {
-      "epoch": 0.5,
-      "grad_norm": 5.20695686340332,
+      "epoch": 0.25,
+      "grad_norm": 5.8763322830200195,
       "learning_rate": 4e-05,
-      "loss": 1.5303,
+      "loss": 1.5735,
       "step": 3
     },
     {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 4.481665134429932,
-      "learning_rate": 6e-05,
-      "loss": 1.394,
-      "step": 4
+      "epoch": 0.25,
+      "eval_loss": 1.4451128244400024,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 7.215,
+      "step": 3
     },
     {
-      "epoch": 0.6666666666666666,
-      "eval_loss": 1.2689329385757446,
-      "eval_runtime": 0.3021,
-      "eval_samples_per_second": 9.93,
-      "eval_steps_per_second": 6.62,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 4.730646133422852,
+      "learning_rate": 6e-05,
+      "loss": 1.2767,
       "step": 4
     },
     {
-      "epoch": 0.8333333333333334,
-      "grad_norm": 3.2430155277252197,
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.4440248012542725,
       "learning_rate": 8e-05,
-      "loss": 1.2373,
+      "loss": 1.3011,
       "step": 5
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 2.6539690494537354,
+      "epoch": 0.5,
+      "grad_norm": 2.8259096145629883,
       "learning_rate": 0.0001,
-      "loss": 1.0206,
+      "loss": 1.0815,
       "step": 6
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 0.7840422987937927,
-      "eval_runtime": 0.3266,
-      "eval_samples_per_second": 9.185,
-      "eval_steps_per_second": 6.123,
+      "epoch": 0.5,
+      "eval_loss": 0.816199779510498,
+      "eval_runtime": 0.4516,
+      "eval_samples_per_second": 6.643,
+      "eval_steps_per_second": 6.643,
       "step": 6
     }
   ],
   "logging_steps": 1,
-  "max_steps": 6,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 2,
+  "save_steps": 3,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -95,12 +87,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 1109738548887552.0,
   "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 sha256:74dcf4a29346d06a18985986c93532599870827345febcfc1739afefe0e2e2b9
+oid sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
 size 6776