Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "down_proj",
-    "v_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_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:eaf0d929dd0f8e2abf3f72312ab980bf927289a5c74dd138c173731935d5d20c
+oid sha256:0c2606fe1d8481601f53d7e2a44ac391784fde273b8fdf73ad578a03a0b8f7f7
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce84ed89db84f735344f10ac2873771a451bd4efe6bc18676953835cb737b1f
+oid sha256:20e5fbe48ce25bdc6be79fec4ca2effd3d4baec950657c4ccf7efa4afdc0c822
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc00d86e6324507dafbd196fc60a31ea771017fd4638a75df6dadc20c1a95ea3
+oid sha256:7f7e152463b88a8b211d8bfa23996dbf5534a9998e5bca50d566b37fb32a7418
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018285714285714287,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2377142857142857,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.018285714285714287,
       "eval_loss": 1.6030340194702148,
-      "eval_runtime": 22.3335,
-      "eval_samples_per_second": 16.522,
-      "eval_steps_per_second": 2.104,
+      "eval_runtime": 22.4221,
+      "eval_samples_per_second": 16.457,
+      "eval_steps_per_second": 2.096,
       "step": 1
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.11251654475927353,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.5836,
+      "step": 10
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "eval_loss": 1.5457781553268433,
+      "eval_runtime": 22.3246,
+      "eval_samples_per_second": 16.529,
+      "eval_steps_per_second": 2.105,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2624155727953920.0,
+  "total_flos": 3.411402446340096e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4e854765d81412e58d86468a2ef6a7780aa73df9f021e14d99e72550f1bd9c
+oid sha256:1763280b24f1f2d5dd983a48e6259d415860c3524f5d5ba0e3f42eb892a630ed
 size 6776