Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988ee46c408a07b7a0fad4b1c0ff670aad8799b9b267896a4244fcdba18e552b
+oid sha256:51b192a7b70db1934dba0f9d9a34e18e69ec65f39168a14efeb68bab0d415c94
 size 484047087

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25580c636627541ce14bdc779eade94125dc6177b2aa83645d2ef2395daaa273
+oid sha256:5491c1eb83ad0255fa2195ad3d2057886c2ddfe459b2d0d86d130dd460f2c126
 size 242012923

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5119b201c0c8ce8aa50d2ab24369c5098c578a46726686f668686b71cefedc
+oid sha256:da5f59398b256310b16e5b8660f3abc262dd46e94f7c4ef1ca2deb4421e45807
 size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1adf8adfe4057346d099df92e326b1ad5fa2d44a51313442fb1c361bdd9899b0
+oid sha256:40cdf027dfcd88dd0425eb5ed9a78e9f857bde345f0e7a339091c24672288322
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec642b785cc0a9d07d3c78d3a67e22851ce9b6c0ecba48c9d62722bf933255a
+oid sha256:48a2bf23ad9a52f893b5c83c2acdf47455196bb0c79c1006037401a5216124d5
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.7792329788208008,
-  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-5500",
-  "epoch": 1.76,
-  "global_step": 5500,
+  "best_metric": 0.7785006165504456,
+  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-6000",
+  "epoch": 1.92,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -226,11 +226,31 @@
       "eval_samples_per_second": 75.808,
       "eval_steps_per_second": 2.388,
       "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.507090645737192e-05,
+      "loss": 0.5956,
+      "step": 6000
+    },
+    {
+      "epoch": 1.92,
+      "eval_bleu": 0.129401969984806,
+      "eval_exact_match": 0.1605,
+      "eval_loss": 0.7785006165504456,
+      "eval_rouge1": 0.5640650180352025,
+      "eval_rouge2": 0.39806305672301234,
+      "eval_rougeL": 0.5469935550994057,
+      "eval_rougeLsum": 0.554556710156975,
+      "eval_runtime": 27.3051,
+      "eval_samples_per_second": 73.246,
+      "eval_steps_per_second": 2.307,
+      "step": 6000
     }
   ],
   "max_steps": 31250,
   "num_train_epochs": 10,
-  "total_flos": 2.340678090306355e+16,
+  "total_flos": 2.5532806050349056e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25580c636627541ce14bdc779eade94125dc6177b2aa83645d2ef2395daaa273
+oid sha256:5491c1eb83ad0255fa2195ad3d2057886c2ddfe459b2d0d86d130dd460f2c126
 size 242012923