Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "down_proj",
     "gate_proj",
+    "o_proj",
     "up_proj",
+    "down_proj",
     "k_proj",
-    "v_proj",
-    "o_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 sha256:71c2b5e5da46c7c9e5945e7ea784a36848284f062ca3f0c18c8cd5a6aabdfc26
+oid sha256:6f9dbe0247a0649b26219c622d4ce878717fbd6419f6a9b5d72429f35abc4e53
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d0cbaa6f4a95d1389654a3fd30e20cac2346076e3cea0d7f3711d73a597f4f2
+oid sha256:b0fc5e25498c1c428cc3d252185df9fc020d5b830ddbb18f4394bcc9486ef4c9
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb5dd3632f621f63027a71316dd458a1d0eb2cb6f6bdb9c2be6da1bb386cb19
+oid sha256:4479d8612262ecedc656e3fb719b965a26864f43306d791dee922d685b13b6f5
 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": 0.0009095043201455207,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01182355616189177,
+  "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": 0.0009095043201455207,
       "eval_loss": 3.3733649253845215,
-      "eval_runtime": 18.3447,
-      "eval_samples_per_second": 25.239,
-      "eval_steps_per_second": 12.647,
+      "eval_runtime": 17.8696,
+      "eval_samples_per_second": 25.91,
+      "eval_steps_per_second": 12.983,
       "step": 1
+    },
+    {
+      "epoch": 0.004547521600727604,
+      "grad_norm": 1.3267475366592407,
+      "learning_rate": 5e-05,
+      "loss": 3.4053,
+      "step": 5
+    },
+    {
+      "epoch": 0.009095043201455207,
+      "grad_norm": 1.4344451427459717,
+      "learning_rate": 0.0001,
+      "loss": 3.0979,
+      "step": 10
+    },
+    {
+      "epoch": 0.009095043201455207,
+      "eval_loss": 3.200488805770874,
+      "eval_runtime": 17.662,
+      "eval_samples_per_second": 26.214,
+      "eval_steps_per_second": 13.136,
+      "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": 82004866498560.0,
+  "total_flos": 1066063264481280.0,
   "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:a046722d47dcfef77b6b45897fb6f05ddebbf2c12fb13b267b0ce6b025fc626f
+oid sha256:88f27e6fb3dc8629f437c3efbe6fecc2f87925059be6ea4e24ac1970bef21b63
 size 6776