Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e201ce5b2fdb493f8c3146ed531907de3ac4bfdc57cc21e6be1b3b4e0b518c0
+oid sha256:4d5b02db0d61c0cef8a548cd425fd2e049fb7fc24afac453dc5f53b9903df48e
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7a50f95938380c2ec3f475f5abaf613180d604f2765cdc2e035c7320c87291
+oid sha256:cea93e352d89157e242c86d6e59074a13f961c2c934e8b43508f69f44f86b4ef
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486942267fe9e9626b2afeb9aa1e52deb2eb52f3c6033a0fffce7ee5b86e5efa
+oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
 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": 4.028035124466285e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005236445661806171,
+  "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": 4.028035124466285e-05,
       "eval_loss": 1.3375216722488403,
-      "eval_runtime": 837.3032,
-      "eval_samples_per_second": 12.485,
-      "eval_steps_per_second": 6.243,
+      "eval_runtime": 835.7879,
+      "eval_samples_per_second": 12.508,
+      "eval_steps_per_second": 6.254,
       "step": 1
+    },
+    {
+      "epoch": 0.00020140175622331428,
+      "grad_norm": 2.134361982345581,
+      "learning_rate": 5e-05,
+      "loss": 1.218,
+      "step": 5
+    },
+    {
+      "epoch": 0.00040280351244662856,
+      "grad_norm": 2.4398152828216553,
+      "learning_rate": 0.0001,
+      "loss": 1.1661,
+      "step": 10
+    },
+    {
+      "epoch": 0.00040280351244662856,
+      "eval_loss": 0.8356062769889832,
+      "eval_runtime": 835.3909,
+      "eval_samples_per_second": 12.514,
+      "eval_steps_per_second": 6.257,
+      "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": 191109141626880.0,
+  "total_flos": 2484418841149440.0,
   "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 sha256:330e0432d84d30fd60b81500a57951f7cecd96a14247bf75c0d297ec000d92dc
+oid sha256:aa1123d5ce1dc43d6d49e978d6f682b00c4bc1eeb800a8390def91783106b393
 size 6776