Training in progress, step 8500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1873b7c859425f0e26f2347fb91e6a776cba2e48839820c2dcea4e22bc7fbc67
+oid sha256:3a85eb263deb4c62619accbaf79f0b4b520c964ea72ccb01a610c00d14c2e6c1
 size 484047087

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23299a7aeba471b07c347aceb29e5198305d8414f4dd4b21f79fc14a4592d39
+oid sha256:4b276e716795aaff1cff242b0a235b4a334c0f04be0f4527656426fdc25e0374
 size 242012923

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9038bd13cee7be809b870072293469c3cd227459e6b82a61f4cf6abfd04c52
+oid sha256:a6fe5e55a28bec87da43da634edefd5e9737d0fb7942ab5d1595a5149b1148b6
 size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0316325edea77248486ca0e79ad8e8ee0b7725685c3d831ab06f04629fb1ef89
+oid sha256:97aa4284d30c55c9de6eb4425ce0d2728af80a248d437264944c01a2e6a6265c
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34db57be1d8dc6c076b5589b33fe55a93138c1738acd1cce1da407f6d1d9bb29
+oid sha256:f97dba5218102cb7a6dbc477aa202196bb52ab595fab0e37adc58120c6e0a955
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.767312228679657,
-  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-8000",
-  "epoch": 2.56,
-  "global_step": 8000,
+  "best_metric": 0.7641937732696533,
+  "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-8500",
+  "epoch": 2.7199999999999998,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -326,11 +326,31 @@
       "eval_samples_per_second": 74.896,
       "eval_steps_per_second": 2.359,
       "step": 8000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 7.664971199514939e-05,
+      "loss": 0.5322,
+      "step": 8500
+    },
+    {
+      "epoch": 2.72,
+      "eval_bleu": 0.13498312180179964,
+      "eval_exact_match": 0.1665,
+      "eval_loss": 0.7641937732696533,
+      "eval_rouge1": 0.5707696930577069,
+      "eval_rouge2": 0.403346138073659,
+      "eval_rougeL": 0.5527280072901636,
+      "eval_rougeLsum": 0.5605579795104842,
+      "eval_runtime": 26.4882,
+      "eval_samples_per_second": 75.505,
+      "eval_steps_per_second": 2.378,
+      "step": 8500
     }
   ],
   "max_steps": 31250,
   "num_train_epochs": 10,
-  "total_flos": 3.4018432483590144e+16,
+  "total_flos": 3.614193688982323e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23299a7aeba471b07c347aceb29e5198305d8414f4dd4b21f79fc14a4592d39
+oid sha256:4b276e716795aaff1cff242b0a235b4a334c0f04be0f4527656426fdc25e0374
 size 242012923