Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
     "k_proj",
-    "o_proj",
+    "q_proj",
     "down_proj",
     "up_proj",
-    "q_proj"
+    "o_proj",
+    "gate_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 sha256:52f5003075a2993d2849d3d2fb6d523e333cc1db77cbad5dbba39684a97ff749
+oid sha256:61db5b4f71ef952b42be6463362e638adaae812a3a508a0c7179d05dc19d05bd
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9f8df30b4c4ab41b628b5c13f966df15894c40426c43fefba021499ba27ba2
+oid sha256:94945125478cf194bf218ba644b26d596a98d2ce332d82d8adca2cb6072efe33
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c13c869668763a7351512d7ac5372aa182e9187d48660a622ae514485f0010fc
+oid sha256:151e353028597ac3bbcb27a88e2d4f6b066dcfb6ec28e51e087826b0b1cba8f6
 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": 0.0018501387604070306,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.024051803885291396,
+  "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": 0.0018501387604070306,
       "eval_loss": 3.789647102355957,
-      "eval_runtime": 14.5726,
-      "eval_samples_per_second": 15.646,
-      "eval_steps_per_second": 7.823,
+      "eval_runtime": 14.6466,
+      "eval_samples_per_second": 15.567,
+      "eval_steps_per_second": 7.783,
       "step": 1
+    },
+    {
+      "epoch": 0.009250693802035153,
+      "grad_norm": 3.147674798965454,
+      "learning_rate": 5e-05,
+      "loss": 3.5633,
+      "step": 5
+    },
+    {
+      "epoch": 0.018501387604070305,
+      "grad_norm": 4.135693550109863,
+      "learning_rate": 0.0001,
+      "loss": 3.0784,
+      "step": 10
+    },
+    {
+      "epoch": 0.018501387604070305,
+      "eval_loss": 2.5756938457489014,
+      "eval_runtime": 14.7893,
+      "eval_samples_per_second": 15.417,
+      "eval_steps_per_second": 7.708,
+      "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": 164009732997120.0,
+  "total_flos": 2132126528962560.0,
   "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 sha256:0042888ac2d2bf723815438b5328f882f6325d313b0509749129b582eaf65e21
+oid sha256:30fbde4f10bc42b534c0266e3d004f45a46e0d59cd3c9dbbfe8dcabc0bbdbc78
 size 6776