Training in progress, epoch 0, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-350m",
+  "_name_or_path": "ccore/getcode-350m",
   "_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 sha256:76fb4fc866b4e3835fde5620d852dd3acf6af67a2f03ddba887ae93a33393041
+oid sha256:c6eb30abb27564021cea167598c5ddb6a1a8f868ac6b92ffe0543f5a7a46e9b0
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1faa1431821eeb0aca3ae47c122491c89e7c0d34b6a910eeabb62cdffa9be6e9
+oid sha256:d9676afafecf7fb77642108b2de350df7aca957ee50de7f950864eede7982abf
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb10c9d6bc9fa712342ab2014e39173dc6d0c92e3482143e2f8eef0197ae6c40
+oid sha256:9ec3fe20ffab29cf5a7067a7c115500a3cceb41380bf24d8b0e8e8acb7b3febc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c441f68d34987b8578be1b29313268756039e66819fc49dbcf77e0d1c8721b2c
+oid sha256:6b26c31a464e4d70e05b8c509f8a98e616933f6fc0a3fc53a30a9375eea4c0b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,62 +1,24 @@
 {
-  "best_metric": 2.431854248046875,
-  "best_model_checkpoint": "./opt_trained1/checkpoint-268",
-  "epoch": 4.0,
+  "best_metric": 6.1056413650512695,
+  "best_model_checkpoint": "./opt_trained1/checkpoint-201",
+  "epoch": 0.9956656346749226,
   "eval_steps": 500,
-  "global_step": 1072,
+  "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": 2.431854248046875,
-      "eval_runtime": 207.1314,
-      "eval_samples_per_second": 13.788,
-      "eval_steps_per_second": 1.724,
-      "step": 268
-    },
-    {
-      "epoch": 1.8664799253034547,
-      "grad_norm": 312980.71875,
-      "learning_rate": 0.00036254681647940074,
-      "loss": 2.4781,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.474102258682251,
-      "eval_runtime": 207.1259,
-      "eval_samples_per_second": 13.789,
-      "eval_steps_per_second": 1.724,
-      "step": 536
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 4.4594879150390625,
-      "eval_runtime": 207.2002,
-      "eval_samples_per_second": 13.784,
-      "eval_steps_per_second": 1.723,
-      "step": 804
-    },
-    {
-      "epoch": 3.7320261437908497,
-      "grad_norm": 664899.9375,
-      "learning_rate": 0.0003250936329588015,
-      "loss": 2.3939,
-      "step": 1000
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 7.311771869659424,
-      "eval_runtime": 207.1535,
-      "eval_samples_per_second": 13.787,
-      "eval_steps_per_second": 1.723,
-      "step": 1072
+      "epoch": 0.9956656346749226,
+      "eval_loss": 6.1056413650512695,
+      "eval_runtime": 155.9076,
+      "eval_samples_per_second": 13.809,
+      "eval_steps_per_second": 1.732,
+      "step": 201
     }
   ],
   "logging_steps": 500,
-  "max_steps": 5340,
+  "max_steps": 4020,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
@@ -72,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.239794057183232e+16,
+  "total_flos": 1.3617405984964608e+16,
   "train_batch_size": 12,
   "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:e7ea0facaa868ab91cf2092a8d2d40baf30425ddd42bb13a273f26d1ab6a2382
+oid sha256:182ed8daa5b93239b0293478a0bba7e3cc285264595500bcf2beff9453ed7fb3
 size 5368