Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "fc_out",
-    "out_proj",
     "k_proj",
     "q_proj",
-    "fc_in",
-    "v_proj"
+    "out_proj",
+    "v_proj",
+    "fc_in"
   ],
   "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 sha256:716c1ed72032ed0f6eb817957fda6845ae94b5b1d784537eee7cfedcef67018d
+oid sha256:fcc3635c3af9aba380d4c1118c9f79227cb06f9e8de884f97564a0bcada0efed
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f74d07d48d3a28ed72f3088a388e33da2c2e0005fa20bd7536244e4b28c0493
+oid sha256:f42f6965441e3678cc635c8f133da948e72ebb61d05d423ed048d820326b4740
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e524472fcfd24c8d044b3f4c8529a5a005f27e58783e50783b40ed22791b1241
+oid sha256:0021bdd5d4dfd189ca068b881930f409d18a94214a1f01661c34c771e5929764
 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": 0.00018889308651303362,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002455610124669437,
+  "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": 0.00018889308651303362,
       "eval_loss": 0.6436558961868286,
-      "eval_runtime": 309.1654,
-      "eval_samples_per_second": 7.213,
-      "eval_steps_per_second": 3.606,
+      "eval_runtime": 309.7106,
+      "eval_samples_per_second": 7.2,
+      "eval_steps_per_second": 3.6,
       "step": 1
+    },
+    {
+      "epoch": 0.0009444654325651682,
+      "grad_norm": 0.8755938410758972,
+      "learning_rate": 5e-05,
+      "loss": 2.3002,
+      "step": 5
+    },
+    {
+      "epoch": 0.0018889308651303363,
+      "grad_norm": 0.9676241874694824,
+      "learning_rate": 0.0001,
+      "loss": 2.4821,
+      "step": 10
+    },
+    {
+      "epoch": 0.0018889308651303363,
+      "eval_loss": 0.6001492142677307,
+      "eval_runtime": 310.6428,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 3.589,
+      "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": 252068320487424.0,
+  "total_flos": 3492946726754304.0,
   "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 sha256:2b100d6d88b9ea2800f1bcda8d04b1d9ea91fd693802d9ef9a8fbbb458bcb199
+oid sha256:1b48a7d07929b385e4bbd4ccc17a7b4d8d95f60e630410f75a0072654236f1db
 size 6776