Training in progress, step 36000

all_results.json

@@ -5,8 +5,8 @@
     "eval_samples_per_second": 0.81,
     "eval_steps_per_second": 0.203,
     "eval_wer": 29.205723913714138,
-    "train_loss": 0.7804906897136143,
-    "train_runtime": 406099.0091,
-    "train_samples_per_second": 0.689,
-    "train_steps_per_second": 0.086
+    "train_loss": 1.5390448555129346e-05,
+    "train_runtime": 6.8399,
+    "train_samples_per_second": 40936.549,
+    "train_steps_per_second": 5117.069
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad2bde5feeaec1a9101e1776c6370a1ba226a08d8ed0cbf0fdd980af2ad1150
+oid sha256:2793cdc0144994fe021fe306cd3dab078f8e2a27184dc7a8734c2650705c9db5
 size 4936567968

runs/Feb04_08-43-21_ip-10-0-3-5.eu-west-1.compute.internal/events.out.tfevents.1707036244.ip-10-0-3-5.eu-west-1.compute.internal.10679.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a6a682062abf19d149cbf3e928b6f72a7b99231e75383176c59544e5e7a8a9
+size 11942

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.18,
-    "train_loss": 0.7804906897136143,
-    "train_runtime": 406099.0091,
-    "train_samples_per_second": 0.689,
-    "train_steps_per_second": 0.086
+    "train_loss": 1.5390448555129346e-05,
+    "train_runtime": 6.8399,
+    "train_samples_per_second": 40936.549,
+    "train_steps_per_second": 5117.069
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 29.205723913714138,
   "best_model_checkpoint": "./hamsa-pretrained/checkpoint-35000",
-  "epoch": 0.17544035529178237,
+  "epoch": 0.17544536787336215,
   "eval_steps": 1000,
-  "global_step": 35000,
+  "global_step": 35001,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8725,12 +8725,12 @@
     },
     {
       "epoch": 0.18,
-      "step": 35000,
-      "total_flos": 4.753690066944e+20,
-      "train_loss": 0.7804906897136143,
-      "train_runtime": 406099.0091,
-      "train_samples_per_second": 0.689,
-      "train_steps_per_second": 0.086
+      "step": 35001,
+      "total_flos": 4.7538258866601984e+20,
+      "train_loss": 1.5390448555129346e-05,
+      "train_runtime": 6.8399,
+      "train_samples_per_second": 40936.549,
+      "train_steps_per_second": 5117.069
     }
   ],
   "logging_steps": 25,
@@ -8738,7 +8738,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1000,
-  "total_flos": 4.753690066944e+20,
+  "total_flos": 4.7538258866601984e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac3075244d6d9afe4f493d1fbf75070decb9ab6fd1bd6f21224543f2e1206e0
+oid sha256:74b9e93f07ccec52bc6245b5cb3e4e9324c69da5b5fc95cb33c1098eb297b715
 size 4856