Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "k_proj",
+    "down_proj",
     "gate_proj",
     "v_proj",
+    "o_proj",
     "up_proj",
-    "down_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4742d00dcf0f73b259c864520ceb30ecd36c6e5c2e9102ffbde78cb2201a2b6
+oid sha256:56d29b14109af0e68e21142079dd1632f9e502fb1a05cfc12a4cec329b9bc4c4
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b871a12774564f978efe1fc17b9178c8b816136b1e8b8ae4d9a01f81ca86697b
+oid sha256:b3184205fa55c0c30cc8363889e43a3c17b0a3f43e22d3d9f47c370098613175
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 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": 0.0012315270935960591,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01600985221674877,
+  "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": 0.0012315270935960591,
       "eval_loss": 10.3784761428833,
-      "eval_runtime": 16.5943,
-      "eval_samples_per_second": 329.692,
-      "eval_steps_per_second": 41.219,
+      "eval_runtime": 8.6523,
+      "eval_samples_per_second": 632.319,
+      "eval_steps_per_second": 79.054,
       "step": 1
+    },
+    {
+      "epoch": 0.012315270935960592,
+      "grad_norm": 0.33271121978759766,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 166.0521,
+      "step": 10
+    },
+    {
+      "epoch": 0.012315270935960592,
+      "eval_loss": 10.37819766998291,
+      "eval_runtime": 8.8426,
+      "eval_samples_per_second": 618.711,
+      "eval_steps_per_second": 77.353,
+      "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": 410637041664.0,
+  "total_flos": 5363946356736.0,
   "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 sha256:384b8ad71b299f2a30b05508172666891e1c9c7a24a717ef2f8c9f89725e3dd6
+oid sha256:f4876531e17752e38a8d2ad0489feddf72096e580ba36b7cbb78e866dc63c5bd
 size 6776