Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "k_proj",
     "up_proj",
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "down_proj",
-    "o_proj"
+    "k_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:cfcf11ffc2acc5a0e044b08996236403d6d758bc1cb1dede5fc380a41fc4431c
+oid sha256:f16482d171cbe3c2bc3d01f7cf97ae43697c571ee8dac1fa342ed2882cf9f440
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f068e78a9723cda68d52e53f514b736226ef28d8ba4d8ff05faf4912a4f02f0d
+oid sha256:ce2a6195d93f3bf4d5e786f91b14774685db0d88bfdf1d40f20b80172f8864d4
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
+oid sha256:c5e599ebf8c42bf4256978eb4e60b65fa52201162f66abf71b04010cf02aa5e2
 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": 0.0001626743665866851,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002114766765626906,
+  "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": 0.0001626743665866851,
       "eval_loss": NaN,
-      "eval_runtime": 124.5196,
-      "eval_samples_per_second": 20.792,
-      "eval_steps_per_second": 10.4,
+      "eval_runtime": 125.1033,
+      "eval_samples_per_second": 20.695,
+      "eval_steps_per_second": 10.351,
       "step": 1
+    },
+    {
+      "epoch": 0.0008133718329334255,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.001626743665866851,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.001626743665866851,
+      "eval_loss": NaN,
+      "eval_runtime": 124.1419,
+      "eval_samples_per_second": 20.855,
+      "eval_steps_per_second": 10.432,
+      "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": 68560663609344.0,
+  "total_flos": 891288626921472.0,
   "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:d9318ca13eb873663cd5ff04cf12831ef3d5b1f0d9a70df0ee4d4f113eaee8f9
+oid sha256:290af56a463fc9d504dd01b624eda84be4c318040630523198c3b3e62451fd40
 size 6776