Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
+    "gate_proj",
     "k_proj",
-    "up_proj"
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "o_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:f93df2ccd87e10501e2eb9b39f9bc1e7e4695056b7ecd99388679826f988a16a
+oid sha256:19ba995700e77d8055f832c8f4dbe98e3e3cddc996cb203ff7359f5f991b3ba3
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:4c94de8bb139da26ca61152126e7ff94310d42f939b89b1b3a10badbfd70b6c2
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
+oid sha256:3e5c16706895889777a35907f3d37543aa1a35d1397dbaa0a630f4274e534eb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026490066225165563,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.26490066225165565,
+  "eval_steps": 8,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.026490066225165563,
       "eval_loss": NaN,
-      "eval_runtime": 1.0879,
-      "eval_samples_per_second": 14.707,
-      "eval_steps_per_second": 7.354,
+      "eval_runtime": 1.0781,
+      "eval_samples_per_second": 14.841,
+      "eval_steps_per_second": 7.421,
       "step": 1
+    },
+    {
+      "epoch": 0.13245033112582782,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.2119205298013245,
+      "eval_loss": NaN,
+      "eval_runtime": 0.6857,
+      "eval_samples_per_second": 23.335,
+      "eval_steps_per_second": 11.668,
+      "step": 8
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 38,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 32429825851392.0,
+  "total_flos": 356728084365312.0,
   "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 sha256:7d3bdc90a0bb1aced72b7bbf094b4f96fca93ec066d491274575f95db8cf5770
+oid sha256:0ae4019a88322da1a38532f251b83d01ca9eaf782990553684a31e9cf3c02667
 size 6776