Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-125m",
+  "_name_or_path": "ccore/getcode",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2624e568b01117d2b53cb7c2188e6045c01a4fc93c512d290d0a67777429795
+oid sha256:1d349f0b58b03412a4d76688dfda12d87a743414b7487492696f39d7eaeba5c6
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e74e67aa5ad57d75f3d0dcd7d8de37fe999a1e88db87fe66da4b00a4f5503669
+oid sha256:b60e7bdba8f1f8bf41e8f0b268a6b237b458c2393a1e6fb9d3874d6e8c4f2084
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf46b4780f5a7b00f2a03861162972b05a45808ee3e2cef5e168534d2375ef68
+oid sha256:91c4d4e1a099584438df8e6abdc3506fd74ad79b44065cd75495056a300ae47b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32464645d17632bf0c2e014289631964997d99b1535854552ce0dbdce65b6584
+oid sha256:2639f3873201909b5b19d566bebe21cf251cebc7007a2f465554f2fe27921d6a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,168 +1,24 @@
 {
-  "best_metric": 1.3129278421401978,
-  "best_model_checkpoint": "./opt_trained/checkpoint-418",
-  "epoch": 19.0,
+  "best_metric": 1.0177865028381348,
+  "best_model_checkpoint": "./opt_trained/checkpoint-201",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 418,
+  "global_step": 201,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.8587957620620728,
-      "eval_runtime": 8.062,
-      "eval_samples_per_second": 37.212,
-      "eval_steps_per_second": 9.303,
-      "step": 22
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 1.4884560108184814,
-      "eval_runtime": 8.0476,
-      "eval_samples_per_second": 37.278,
-      "eval_steps_per_second": 9.32,
-      "step": 44
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 1.3922361135482788,
-      "eval_runtime": 8.0491,
-      "eval_samples_per_second": 37.271,
-      "eval_steps_per_second": 9.318,
-      "step": 66
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 1.3830264806747437,
-      "eval_runtime": 8.0646,
-      "eval_samples_per_second": 37.2,
-      "eval_steps_per_second": 9.3,
-      "step": 88
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 1.354698896408081,
-      "eval_runtime": 8.0581,
-      "eval_samples_per_second": 37.23,
-      "eval_steps_per_second": 9.307,
-      "step": 110
-    },
-    {
-      "epoch": 6.0,
-      "eval_loss": 1.3555606603622437,
-      "eval_runtime": 8.0406,
-      "eval_samples_per_second": 37.311,
-      "eval_steps_per_second": 9.328,
-      "step": 132
-    },
-    {
-      "epoch": 7.0,
-      "eval_loss": 1.367162823677063,
-      "eval_runtime": 8.0926,
-      "eval_samples_per_second": 37.071,
-      "eval_steps_per_second": 9.268,
-      "step": 154
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 1.350898027420044,
-      "eval_runtime": 8.0696,
-      "eval_samples_per_second": 37.177,
-      "eval_steps_per_second": 9.294,
-      "step": 176
-    },
-    {
-      "epoch": 9.0,
-      "eval_loss": 1.3414418697357178,
-      "eval_runtime": 8.0548,
-      "eval_samples_per_second": 37.245,
-      "eval_steps_per_second": 9.311,
-      "step": 198
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 1.3427915573120117,
-      "eval_runtime": 8.0486,
-      "eval_samples_per_second": 37.274,
-      "eval_steps_per_second": 9.318,
-      "step": 220
-    },
-    {
-      "epoch": 11.0,
-      "eval_loss": 1.3360599279403687,
-      "eval_runtime": 8.0639,
-      "eval_samples_per_second": 37.203,
-      "eval_steps_per_second": 9.301,
-      "step": 242
-    },
-    {
-      "epoch": 12.0,
-      "eval_loss": 1.3332167863845825,
-      "eval_runtime": 8.1186,
-      "eval_samples_per_second": 36.952,
-      "eval_steps_per_second": 9.238,
-      "step": 264
-    },
-    {
-      "epoch": 13.0,
-      "eval_loss": 1.3333313465118408,
-      "eval_runtime": 8.1186,
-      "eval_samples_per_second": 36.952,
-      "eval_steps_per_second": 9.238,
-      "step": 286
-    },
-    {
-      "epoch": 14.0,
-      "eval_loss": 1.3279589414596558,
-      "eval_runtime": 8.1077,
-      "eval_samples_per_second": 37.002,
-      "eval_steps_per_second": 9.25,
-      "step": 308
-    },
-    {
-      "epoch": 15.0,
-      "eval_loss": 1.323224663734436,
-      "eval_runtime": 8.1229,
-      "eval_samples_per_second": 36.933,
-      "eval_steps_per_second": 9.233,
-      "step": 330
-    },
-    {
-      "epoch": 16.0,
-      "eval_loss": 1.3214843273162842,
-      "eval_runtime": 8.1269,
-      "eval_samples_per_second": 36.914,
-      "eval_steps_per_second": 9.229,
-      "step": 352
-    },
-    {
-      "epoch": 17.0,
-      "eval_loss": 1.31853449344635,
-      "eval_runtime": 8.1214,
-      "eval_samples_per_second": 36.939,
-      "eval_steps_per_second": 9.235,
-      "step": 374
-    },
-    {
-      "epoch": 18.0,
-      "eval_loss": 1.3142348527908325,
-      "eval_runtime": 8.1317,
-      "eval_samples_per_second": 36.893,
-      "eval_steps_per_second": 9.223,
-      "step": 396
-    },
-    {
-      "epoch": 19.0,
-      "eval_loss": 1.3129278421401978,
-      "eval_runtime": 8.1293,
-      "eval_samples_per_second": 36.903,
-      "eval_steps_per_second": 9.226,
-      "step": 418
+      "eval_loss": 1.0177865028381348,
+      "eval_runtime": 77.0752,
+      "eval_samples_per_second": 37.055,
+      "eval_steps_per_second": 9.264,
+      "step": 201
     }
   ],
   "logging_steps": 500,
-  "max_steps": 420,
+  "max_steps": 4000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -178,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3478982183936e+16,
+  "total_flos": 6766351096320000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0017a8d69cb5eb07db982774b9507cf45f8391374e94aa47a6813fcd16581db9
+oid sha256:47fa39153c41cc8f065c362dc73a00a51e07e05c31b9fdd0fbc0c294dd936d7b
 size 5368