Training in progress, step 5500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5beade581370905e0292a2365254ab36702badd368e972582e67f69bc6dc15a
+oid sha256:988ee46c408a07b7a0fad4b1c0ff670aad8799b9b267896a4244fcdba18e552b
 size 484047087

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deeaca81b35d434ce5b6b530e89307b56cda4b78a599ccac19b2479886dedee6
+oid sha256:25580c636627541ce14bdc779eade94125dc6177b2aa83645d2ef2395daaa273
 size 242012923

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bf8a79e4de64e1a9640e42c2e98fc6a9068235278df19d118fa324172535fc
+oid sha256:0b5119b201c0c8ce8aa50d2ab24369c5098c578a46726686f668686b71cefedc
 size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8b569fde0bf5d944ad8405d6ea4df676b1d3706ac5880cb76e64fcf88c36e9
+oid sha256:1adf8adfe4057346d099df92e326b1ad5fa2d44a51313442fb1c361bdd9899b0
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92136d2222c9ea21a1988022b25a43dfa694cbf1fc2afc83b23d5ad1f8c2ffde
+oid sha256:6ec642b785cc0a9d07d3c78d3a67e22851ce9b6c0ecba48c9d62722bf933255a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.782397449016571,
-  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-5000",
-  "epoch": 1.6,
-  "global_step": 5000,
+  "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,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,11 +206,31 @@
       "eval_samples_per_second": 73.561,
       "eval_steps_per_second": 2.317,
       "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.675514534981643e-05,
+      "loss": 0.608,
+      "step": 5500
+    },
+    {
+      "epoch": 1.76,
+      "eval_bleu": 0.13144704649097816,
+      "eval_exact_match": 0.163,
+      "eval_loss": 0.7792329788208008,
+      "eval_rouge1": 0.5663801985181786,
+      "eval_rouge2": 0.3996756504619762,
+      "eval_rougeL": 0.5490225477397204,
+      "eval_rougeLsum": 0.556696752293008,
+      "eval_runtime": 26.3826,
+      "eval_samples_per_second": 75.808,
+      "eval_steps_per_second": 2.388,
+      "step": 5500
     }
   ],
   "max_steps": 31250,
   "num_train_epochs": 10,
-  "total_flos": 2.1280992603930624e+16,
+  "total_flos": 2.340678090306355e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deeaca81b35d434ce5b6b530e89307b56cda4b78a599ccac19b2479886dedee6
+oid sha256:25580c636627541ce14bdc779eade94125dc6177b2aa83645d2ef2395daaa273
 size 242012923