Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "k_proj",
-    "v_proj",
+    "o_proj",
     "up_proj",
     "gate_proj",
-    "down_proj"
+    "down_proj",
+    "v_proj",
+    "q_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 sha256:3f642c29a19f7001f56d25d8bf26f112769edde5998d20456a4f84a3ccb79c4f
+oid sha256:e8d78fc55931fef15003b7d72660ecfd805c587c7dceba9fda53c358711d91f0
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f99784e18df8208396df45bda7276d5425352018dd42722c685ac1604428ea
+oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cbfa962acc4e0861b80331d9e44e15444ab79b41d6c9d6a45df983b4cd0da0
+oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e065525f31fad596045dcb1a608d8ed3886356aa96defc3d15ad81f61b32d3d
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,66 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0467289719626167,
-  "eval_steps": 3,
-  "global_step": 14,
+  "epoch": 0.004678362573099415,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.07476635514018691,
+      "epoch": 0.004678362573099415,
       "eval_loss": NaN,
-      "eval_runtime": 3.5261,
-      "eval_samples_per_second": 25.524,
-      "eval_steps_per_second": 3.403,
+      "eval_runtime": 4.6074,
+      "eval_samples_per_second": 19.534,
+      "eval_steps_per_second": 9.767,
       "step": 1
-    },
-    {
-      "epoch": 0.22429906542056074,
-      "eval_loss": NaN,
-      "eval_runtime": 2.0479,
-      "eval_samples_per_second": 43.947,
-      "eval_steps_per_second": 5.86,
-      "step": 3
-    },
-    {
-      "epoch": 0.4485981308411215,
-      "eval_loss": NaN,
-      "eval_runtime": 2.0416,
-      "eval_samples_per_second": 44.083,
-      "eval_steps_per_second": 5.878,
-      "step": 6
-    },
-    {
-      "epoch": 0.6728971962616822,
-      "eval_loss": NaN,
-      "eval_runtime": 2.0573,
-      "eval_samples_per_second": 43.747,
-      "eval_steps_per_second": 5.833,
-      "step": 9
-    },
-    {
-      "epoch": 0.7476635514018691,
-      "grad_norm": NaN,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.897196261682243,
-      "eval_loss": NaN,
-      "eval_runtime": 2.0385,
-      "eval_samples_per_second": 44.15,
-      "eval_steps_per_second": 5.887,
-      "step": 12
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 14,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 4,
+  "num_train_epochs": 1,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -73,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 7450752489357312.0,
-  "train_batch_size": 8,
+  "total_flos": 32429825851392.0,
+  "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 sha256:8e007adad79ee80e169a9cb8a199868a5773f153a5d83e19f9c42fdbdd8ce7d8
+oid sha256:b4fd832c32d37c277e396a82d9f461949c1b651a2dcb827eadb3718594462d96
 size 6776