Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "k_proj",
     "gate_proj",
-    "down_proj",
+    "o_proj",
     "up_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "v_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 sha256:9eea3643b80ff1a6b826e373aca59a37fc073cfe513f37d422f3492c4d1ac9e3
+oid sha256:06cd67621872cacaaf6447ee9b786a6c6094c8bfa355b64572526e2ee574d174
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b2ef2c4291240d9362e1104e96244bab9c47e9b55c55f37d79b3ee6300fc52
+oid sha256:91e47862edbfaee60942f054bc47a4c0c9440e03a262f1964c72a4e9ce8f42d3
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.00011742257448994569,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.001526493468369294,
+  "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": 0.00011742257448994569,
       "eval_loss": 10.336591720581055,
-      "eval_runtime": 16.6412,
-      "eval_samples_per_second": 215.489,
-      "eval_steps_per_second": 107.744,
+      "eval_runtime": 16.0812,
+      "eval_samples_per_second": 222.993,
+      "eval_steps_per_second": 111.497,
       "step": 1
+    },
+    {
+      "epoch": 0.0005871128724497284,
+      "grad_norm": 0.34773606061935425,
+      "learning_rate": 5e-05,
+      "loss": 10.3354,
+      "step": 5
+    },
+    {
+      "epoch": 0.0011742257448994569,
+      "grad_norm": 0.34472596645355225,
+      "learning_rate": 0.0001,
+      "loss": 10.3331,
+      "step": 10
+    },
+    {
+      "epoch": 0.0011742257448994569,
+      "eval_loss": 10.333213806152344,
+      "eval_runtime": 16.1279,
+      "eval_samples_per_second": 222.347,
+      "eval_steps_per_second": 111.174,
+      "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": 12930908160.0,
+  "total_flos": 168101806080.0,
   "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 sha256:5a875d1e7f60049002edb2fa91c3fb0d927cca54b81e0ac9bb724efb6faa7807
+oid sha256:57d051e3b71ea098a6eaa43bcbb8e647f8940a3ad98503bbefe811d40ed657cb
 size 6776