Training in progress, step 483, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
+    "v_proj",
+    "gate_proj",
     "up_proj",
     "q_proj",
     "down_proj",
-    "v_proj",
-    "gate_proj"
+    "o_proj",
+    "k_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 sha256:59c37ad0118d4ba73506a07d36cc16d598775c6f4156fcf098513e676eae46d7
+oid sha256:825b5fcf901f4a8bf145e82e49be7ae3dc4d2e605a8df0750b726c39d0e0ddd7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f81cd83134e487f3a13ee64592ab90ea6a808bdd198484b98fe4c583885a851
+oid sha256:7205c3860d9fb692d0255a1dc9f90e4f0ee887be3ee0336729f1444d1c387222
 size 43123028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3d7d46a3dd677ad565a1f99d58c76ca3934657b3766d46afd07ffd38585807
+oid sha256:9e0d1a065589c842a1cad837f91ae79543d1e6a0956c85f382c31b3bf06caaad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6159dc73fe2c1c109159c204fa270b8bfc0c35fa7b3beb4676ce2843bdb8cc25
+oid sha256:81fa33a5623739a63cb70ed16900767cdcb5be6dfcafb960417c339c413d0900
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7750046253204346,
-  "best_model_checkpoint": "miner_id_24/checkpoint-138",
-  "epoch": 0.6323024054982818,
-  "eval_steps": 138,
-  "global_step": 414,
+  "best_metric": 0.7824365496635437,
+  "best_model_checkpoint": "miner_id_24/checkpoint-161",
+  "epoch": 0.7376861397479955,
+  "eval_steps": 161,
+  "global_step": 483,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,62 +11,62 @@
     {
       "epoch": 0.0015273004963726614,
       "eval_loss": 1.1177806854248047,
-      "eval_runtime": 44.9202,
-      "eval_samples_per_second": 27.627,
-      "eval_steps_per_second": 3.072,
+      "eval_runtime": 47.3129,
+      "eval_samples_per_second": 26.23,
+      "eval_steps_per_second": 2.917,
       "step": 1
     },
     {
-      "epoch": 0.21076746849942726,
-      "grad_norm": 4.14552640914917,
-      "learning_rate": 0.00039999966577382784,
-      "loss": 3.1374,
-      "step": 138
+      "epoch": 0.24589537991599847,
+      "grad_norm": 4.376685619354248,
+      "learning_rate": 0.00039999913874304673,
+      "loss": 3.1327,
+      "step": 161
     },
     {
-      "epoch": 0.21076746849942726,
-      "eval_loss": 0.7750046253204346,
-      "eval_runtime": 45.473,
-      "eval_samples_per_second": 27.291,
-      "eval_steps_per_second": 3.035,
-      "step": 138
+      "epoch": 0.24589537991599847,
+      "eval_loss": 0.7824365496635437,
+      "eval_runtime": 47.8599,
+      "eval_samples_per_second": 25.93,
+      "eval_steps_per_second": 2.883,
+      "step": 161
     },
     {
-      "epoch": 0.4215349369988545,
-      "grad_norm": 4.95952844619751,
-      "learning_rate": 0.0003999928303802374,
-      "loss": 3.0967,
-      "step": 276
+      "epoch": 0.49179075983199694,
+      "grad_norm": 4.354160308837891,
+      "learning_rate": 0.00039998859290119417,
+      "loss": 3.0925,
+      "step": 322
     },
     {
-      "epoch": 0.4215349369988545,
-      "eval_loss": 0.7872825860977173,
-      "eval_runtime": 45.5264,
-      "eval_samples_per_second": 27.259,
-      "eval_steps_per_second": 3.031,
-      "step": 276
+      "epoch": 0.49179075983199694,
+      "eval_loss": 0.7929523587226868,
+      "eval_runtime": 48.3398,
+      "eval_samples_per_second": 25.672,
+      "eval_steps_per_second": 2.855,
+      "step": 322
     },
     {
-      "epoch": 0.6323024054982818,
-      "grad_norm": 5.273939609527588,
-      "learning_rate": 0.00039997717953866457,
-      "loss": 3.1177,
-      "step": 414
+      "epoch": 0.7376861397479955,
+      "grad_norm": 4.114792346954346,
+      "learning_rate": 0.00039996604852529134,
+      "loss": 3.1385,
+      "step": 483
     },
     {
-      "epoch": 0.6323024054982818,
-      "eval_loss": 0.8026135563850403,
-      "eval_runtime": 45.5948,
-      "eval_samples_per_second": 27.218,
-      "eval_steps_per_second": 3.027,
-      "step": 414
+      "epoch": 0.7376861397479955,
+      "eval_loss": 0.7994549870491028,
+      "eval_runtime": 47.3338,
+      "eval_samples_per_second": 26.218,
+      "eval_steps_per_second": 2.915,
+      "step": 483
     }
   ],
-  "logging_steps": 138,
+  "logging_steps": 161,
   "max_steps": 65400,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
-  "save_steps": 138,
+  "save_steps": 161,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {
@@ -88,7 +88,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.281001608128758e+17,
+  "total_flos": 3.8252062017847296e+17,
   "train_batch_size": 9,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4912750e0525668697e67bfbdf8863ec73474c1ab1b2a41b7a08d6ec81c640
+oid sha256:ad2e424f0d3e85ad37a3506914e5792898a4d236d25069f96df22040323b28f0
 size 6776