Training in progress, step 100, checkpoint

last-checkpoint/adapter_config.json

@@ -25,11 +25,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
-    "v_proj",
+    "o_proj",
     "fc1",
     "k_proj",
-    "o_proj",
+    "v_proj",
+    "fc2",
     "q_proj"
   ],
   "target_parameters": null,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63dc8260aff40fe10f1802ef4e4ff4911fcdb4089428f5f577491a031923296
+oid sha256:09d1498de9aba5c1b498d5d1e4c01cc99ca44d0eee283e3fc184f1f0b7f4a4d4
 size 25205016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d04a3d234a4ccfe437b75561de313aa09d1d11c67002cfb5531772f7d5db1d
+oid sha256:1d5ede4b18e5e7d3d4962e25ab681155139ee39dfec910e201fb2c80d0641fbf
 size 13061131

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a075b6c444b58e18d0a5715eacbbfad0814dba3fd85a911bd35705b4bb6cd13b
+oid sha256:270b2ca40754812f8e112d290e097964475281229bb06ef13f79ceaff75e02a8
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36c94f881e68c8c0b2e422e1ca2454481981ae9880703ee50a9c93f58b4369c
+oid sha256:cb267507c5b729de0d434c88dc7cc212ca3861cb6036f85b5e2d88f5001c4e2a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949190216cc627cd077804191fdbca2cd6ef75095986e43e993625a57c8ca5b4
+oid sha256:d15dc0e5ec3e4cb35d1852a94001879e08c69f7fd1e08d721a40a6ed53fef668
 size 1465

last-checkpoint/trainer_state.json

@@ -2,40 +2,62 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.8,
   "eval_steps": 50,
-  "global_step": 63,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.4,
-      "grad_norm": 5.488026142120361,
-      "learning_rate": 1.4699767430273202e-05,
-      "loss": 8.2641,
+      "epoch": 0.2,
+      "grad_norm": 2.5308005809783936,
+      "learning_rate": 1.99625729663483e-05,
+      "loss": 8.2688,
       "step": 25
     },
     {
-      "epoch": 0.8,
-      "grad_norm": 3.2747206687927246,
-      "learning_rate": 3.207266611027069e-06,
-      "loss": 7.8873,
+      "epoch": 0.4,
+      "grad_norm": 2.6729016304016113,
+      "learning_rate": 1.95447296407255e-05,
+      "loss": 7.7962,
       "step": 50
     },
     {
-      "epoch": 0.8,
-      "eval_loss": 7.82917594909668,
-      "eval_runtime": 25.2233,
-      "eval_samples_per_second": 7.929,
-      "eval_steps_per_second": 0.991,
+      "epoch": 0.4,
+      "eval_loss": 7.424994945526123,
+      "eval_runtime": 36.7897,
+      "eval_samples_per_second": 8.154,
+      "eval_steps_per_second": 1.033,
       "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.4165093898773193,
+      "learning_rate": 1.868180920098644e-05,
+      "loss": 7.272,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.073392152786255,
+      "learning_rate": 1.7414050203223092e-05,
+      "loss": 7.1306,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 6.984020233154297,
+      "eval_runtime": 37.416,
+      "eval_samples_per_second": 8.018,
+      "eval_steps_per_second": 1.016,
+      "step": 100
     }
   ],
   "logging_steps": 25,
-  "max_steps": 63,
+  "max_steps": 375,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 100,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -44,12 +66,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1155062740992000.0,
+  "total_flos": 1848100385587200.0,
   "train_batch_size": 4,
   "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:ea905c1af3e7bfca719cdeb3cde4148328d9d075350e9184703e70b312bca16f
+oid sha256:0e4b60f4de494ccae3eec678a577ff181ad3102e48e3c208ef0d08f2d3eb53f7
 size 5905