Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj",
+    "gate_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
-    "gate_proj"
+    "o_proj",
+    "k_proj",
+    "v_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 sha256:5ef4c6f7cc54411cdede7e80b8136e4bfdbec1de581df71f9ed00577c8a6e094
+oid sha256:826058b85016cb14fc1ae17bfa9dc4fc1a65f07a4d491c25399a5e72e2410f7e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1658ba55bc06c88083b78c019c8e5d9b95b6e5ee29a094564902d13db9e4e9da
+oid sha256:45115f9589ffa03028409b2ee25848a1aa5a86fc4ec6f89cc83763bcd2b86629
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
+oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0072874493927125505,
+  "epoch": 0.008097165991902834,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 5.243322849273682,
+      "grad_norm": 5.4282379150390625,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 48.3021,
-      "eval_samples_per_second": 5.403,
-      "eval_steps_per_second": 5.403,
+      "eval_runtime": 47.0534,
+      "eval_samples_per_second": 5.547,
+      "eval_steps_per_second": 5.547,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.311802387237549,
+      "grad_norm": 5.544086456298828,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,74 +34,81 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5635,
+      "loss": 17.5639,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.010040283203125,
-      "eval_runtime": 47.6629,
-      "eval_samples_per_second": 5.476,
-      "eval_steps_per_second": 5.476,
+      "eval_loss": 16.009519577026367,
+      "eval_runtime": 47.55,
+      "eval_samples_per_second": 5.489,
+      "eval_steps_per_second": 5.489,
       "step": 3
     },
     {
       "epoch": 0.0032388663967611335,
-      "grad_norm": 4.934993267059326,
+      "grad_norm": 5.151875972747803,
       "learning_rate": 6e-05,
-      "loss": 15.4629,
+      "loss": 15.4592,
       "step": 4
     },
     {
       "epoch": 0.004048582995951417,
-      "grad_norm": 6.582982063293457,
+      "grad_norm": 7.000217914581299,
       "learning_rate": 8e-05,
-      "loss": 14.5189,
+      "loss": 14.515,
       "step": 5
     },
     {
       "epoch": 0.004858299595141701,
-      "grad_norm": 7.352993011474609,
+      "grad_norm": 7.624449253082275,
       "learning_rate": 0.0001,
-      "loss": 14.5364,
+      "loss": 14.5286,
       "step": 6
     },
     {
       "epoch": 0.004858299595141701,
-      "eval_loss": 15.222670555114746,
-      "eval_runtime": 47.7487,
-      "eval_samples_per_second": 5.466,
-      "eval_steps_per_second": 5.466,
+      "eval_loss": 15.218199729919434,
+      "eval_runtime": 47.6689,
+      "eval_samples_per_second": 5.475,
+      "eval_steps_per_second": 5.475,
       "step": 6
     },
     {
       "epoch": 0.005668016194331984,
-      "grad_norm": 7.531305313110352,
+      "grad_norm": 7.740715980529785,
       "learning_rate": 0.00012,
-      "loss": 16.2939,
+      "loss": 16.2921,
       "step": 7
     },
     {
       "epoch": 0.006477732793522267,
-      "grad_norm": 8.360276222229004,
+      "grad_norm": 8.621045112609863,
       "learning_rate": 0.00014,
-      "loss": 13.913,
+      "loss": 13.8891,
       "step": 8
     },
     {
       "epoch": 0.0072874493927125505,
-      "grad_norm": 11.318435668945312,
+      "grad_norm": 11.440580368041992,
       "learning_rate": 0.00016,
-      "loss": 13.087,
+      "loss": 13.0894,
       "step": 9
     },
     {
       "epoch": 0.0072874493927125505,
-      "eval_loss": 12.104350090026855,
-      "eval_runtime": 45.0844,
-      "eval_samples_per_second": 5.789,
-      "eval_steps_per_second": 5.789,
+      "eval_loss": 12.089701652526855,
+      "eval_runtime": 47.7959,
+      "eval_samples_per_second": 5.461,
+      "eval_steps_per_second": 5.461,
       "step": 9
+    },
+    {
+      "epoch": 0.008097165991902834,
+      "grad_norm": 14.446660041809082,
+      "learning_rate": 0.00018,
+      "loss": 12.2563,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1478847803424768.0,
+  "total_flos": 1643164226027520.0,
   "train_batch_size": 1,
   "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:a6e1305fc8f281ddb72b2abbc2f99245c4a414545702847872a68fca4d715eef
+oid sha256:ba57699bba9b310c57bde7376897c4b366951d205389ca4384cb9831382eab5b
 size 6776