Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "down_proj",
     "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
     "v_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj"
+    "k_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 sha256:06d86335d9d32b0061da98346dfe976b73fa279a209165cf1d9980f5adf1cd70
+oid sha256:37d0ae3195d67cfb59a01d6fe0d4d3435707f961dfa1d00f4c0047fed9615d1d
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3f786cde787f03079e02cc6ab6adebb254c2e22460fcae80fc35c0beb01240
+oid sha256:e9d579ea8159bc478b9df5439d64a9b2b5cfac7592439b2345c5458e0caaa7a9
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3267679ff13821cd9e55cecebd640b502c34631782995bf2c60986136dabedf
+oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24984384759525297,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00031237797735259666,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.004996876951905059,
-      "eval_loss": 2.7468409538269043,
-      "eval_runtime": 49.4022,
-      "eval_samples_per_second": 27.286,
-      "eval_steps_per_second": 3.421,
+      "epoch": 0.00031237797735259666,
+      "eval_loss": NaN,
+      "eval_runtime": 67.0732,
+      "eval_samples_per_second": 20.097,
+      "eval_steps_per_second": 10.049,
       "step": 1
-    },
-    {
-      "epoch": 0.04996876951905059,
-      "grad_norm": 0.264714777469635,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 2.7375,
-      "step": 10
-    },
-    {
-      "epoch": 0.04996876951905059,
-      "eval_loss": 2.6681642532348633,
-      "eval_runtime": 48.0087,
-      "eval_samples_per_second": 28.078,
-      "eval_steps_per_second": 3.52,
-      "step": 10
-    },
-    {
-      "epoch": 0.09993753903810118,
-      "grad_norm": 0.24352146685123444,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.6298,
-      "step": 20
-    },
-    {
-      "epoch": 0.09993753903810118,
-      "eval_loss": 2.6000702381134033,
-      "eval_runtime": 47.9982,
-      "eval_samples_per_second": 28.084,
-      "eval_steps_per_second": 3.521,
-      "step": 20
-    },
-    {
-      "epoch": 0.14990630855715179,
-      "grad_norm": 0.22053590416908264,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 2.5657,
-      "step": 30
-    },
-    {
-      "epoch": 0.14990630855715179,
-      "eval_loss": 2.552696704864502,
-      "eval_runtime": 47.9533,
-      "eval_samples_per_second": 28.111,
-      "eval_steps_per_second": 3.524,
-      "step": 30
-    },
-    {
-      "epoch": 0.19987507807620236,
-      "grad_norm": 0.23853935301303864,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 2.555,
-      "step": 40
-    },
-    {
-      "epoch": 0.19987507807620236,
-      "eval_loss": 2.5355544090270996,
-      "eval_runtime": 48.1286,
-      "eval_samples_per_second": 28.008,
-      "eval_steps_per_second": 3.511,
-      "step": 40
-    },
-    {
-      "epoch": 0.24984384759525297,
-      "grad_norm": 0.21318064630031586,
-      "learning_rate": 0.0,
-      "loss": 2.548,
-      "step": 50
-    },
-    {
-      "epoch": 0.24984384759525297,
-      "eval_loss": 2.53230357170105,
-      "eval_runtime": 47.849,
-      "eval_samples_per_second": 28.172,
-      "eval_steps_per_second": 3.532,
-      "step": 50
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 50,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -109,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.218452189367501e+16,
-  "train_batch_size": 8,
+  "total_flos": 68560663609344.0,
+  "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:e65387261a0d1eefd38f9ec0c92b115f30a1d0f46dc17ab0f7b95c996209962d
+oid sha256:2b31c3f3b5d4bb38a893a099b5716103782cdc03f1a927b673250cdf2afb0ad4
 size 6776