Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "gate_proj",
-    "v_proj",
-    "o_proj",
     "k_proj",
     "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed18a4c43ace778a01491c6a34ac8c11b5e73d74c8f6f2336d40b287eb5faa0
+oid sha256:a259b2fb107027d1a846834b1771afe83d7ff5fa2e88a4b9045601614b88115c
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b96521b1db2912a9bfae49085aa003070f5a30215881400e0e27bd6776dc8f3
+oid sha256:c250e3bf7f738584eda24910cd892f14b672fb4cc50f161b6e0fb43e4383048b
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bc92371de2dc48fc3204fa3557c31d40e6fd4491378f9e7a4c4fa05636082a
+oid sha256:0a4f0069edb1e06dc358b4ff190f10113fb1ddd26ae17efb126b43600cdb989c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004276702662247407,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00555971346092163,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0004276702662247407,
       "eval_loss": 3.4804275035858154,
-      "eval_runtime": 15.176,
-      "eval_samples_per_second": 64.905,
-      "eval_steps_per_second": 32.485,
+      "eval_runtime": 15.2889,
+      "eval_samples_per_second": 64.426,
+      "eval_steps_per_second": 32.246,
       "step": 1
+    },
+    {
+      "epoch": 0.0021383513311237037,
+      "grad_norm": 0.7456838488578796,
+      "learning_rate": 5e-05,
+      "loss": 3.6062,
+      "step": 5
+    },
+    {
+      "epoch": 0.004276702662247407,
+      "grad_norm": 1.261491060256958,
+      "learning_rate": 0.0001,
+      "loss": 3.4641,
+      "step": 10
+    },
+    {
+      "epoch": 0.004276702662247407,
+      "eval_loss": 3.438182830810547,
+      "eval_runtime": 15.358,
+      "eval_samples_per_second": 64.136,
+      "eval_steps_per_second": 32.1,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "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": 3429265047552.0,
+  "total_flos": 44580445618176.0,
   "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 sha256:6920449911d6a3db33da54c0ec7f9bf0d6bafd8b2beaa0a1fe522c5025c2ed65
+oid sha256:8aba8b9dc6e2cff5f7f3420595b396a2c27261b4b24e2c6e844a3eba43775812
 size 6776