Training in progress, step 21045, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:480a5e2f9450a378fc92e4973711f3797bc46c537cf0abdfb060442407cf3ab9
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281574266
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84c5b0250a84dc0f3baa6c6b288fc1cd5d0865054249365543077c448693090a
|
| 3 |
size 281574266
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a92ef155fa78b173d9b1e38c3936002cf909e55084091c3fd722c835e70548d
|
| 3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7667a62b4506a74425fd1ac76880609051cc562d6283156fe8084b6b93e7cbd4
|
| 3 |
size 988
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f80809aa3af4de00cc2a99808c0f54ee6a223ad41f5853bcfc7d37dd3bc2a1dc
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 16400,
|
| 3 |
"best_metric": 0.2045387562628942,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-16400",
|
| 5 |
-
"epoch": 14.
|
| 6 |
"eval_steps": 400,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1932,6 +1932,20 @@
|
|
| 1932 |
"eval_steps_per_second": 0.429,
|
| 1933 |
"eval_wer": 0.21087533156498675,
|
| 1934 |
"step": 20800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1935 |
}
|
| 1936 |
],
|
| 1937 |
"logging_steps": 100,
|
|
@@ -1946,12 +1960,12 @@
|
|
| 1946 |
"should_evaluate": false,
|
| 1947 |
"should_log": false,
|
| 1948 |
"should_save": true,
|
| 1949 |
-
"should_training_stop":
|
| 1950 |
},
|
| 1951 |
"attributes": {}
|
| 1952 |
}
|
| 1953 |
},
|
| 1954 |
-
"total_flos": 2.
|
| 1955 |
"train_batch_size": 8,
|
| 1956 |
"trial_name": null,
|
| 1957 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 16400,
|
| 3 |
"best_metric": 0.2045387562628942,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-16400",
|
| 5 |
+
"epoch": 14.996971316586496,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 21045,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1932 |
"eval_steps_per_second": 0.429,
|
| 1933 |
"eval_wer": 0.21087533156498675,
|
| 1934 |
"step": 20800
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 14.89363976483164,
|
| 1938 |
+
"grad_norm": 17.801183700561523,
|
| 1939 |
+
"learning_rate": 7.787782915551229e-07,
|
| 1940 |
+
"loss": 1.3892,
|
| 1941 |
+
"step": 20900
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 14.96490290397292,
|
| 1945 |
+
"grad_norm": 12.393946647644043,
|
| 1946 |
+
"learning_rate": 2.9204185933317107e-07,
|
| 1947 |
+
"loss": 1.4323,
|
| 1948 |
+
"step": 21000
|
| 1949 |
}
|
| 1950 |
],
|
| 1951 |
"logging_steps": 100,
|
|
|
|
| 1960 |
"should_evaluate": false,
|
| 1961 |
"should_log": false,
|
| 1962 |
"should_save": true,
|
| 1963 |
+
"should_training_stop": true
|
| 1964 |
},
|
| 1965 |
"attributes": {}
|
| 1966 |
}
|
| 1967 |
},
|
| 1968 |
+
"total_flos": 2.736164082548736e+19,
|
| 1969 |
"train_batch_size": 8,
|
| 1970 |
"trial_name": null,
|
| 1971 |
"trial_params": null
|