Training in progress, step 1750000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +383 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 893439185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c223f21c9f3d69fb40b6ad537a2d1e1726b01ec615931fd84b4f155a73edb6cb
|
| 3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4b2f64ee4b8a3f1cf3d86fb133d82c77bc0f7052c00d93cb35fb4180acc8509
|
| 3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e052c7897af7d62d87b26b3f0036377845bb2408ce5c5d3e7b4078dbe5f611ef
|
| 3 |
size 21643
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af6d04926cbb05a843491ada6b24ca053dbb81e1dc7c6706a5415b4d4cca0e78
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd9e8ca586c336641c0b85f2a85288a9eeaaab808e84d3e0180b33f991192ef6
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -12926,11 +12926,391 @@
|
|
| 12926 |
"eval_samples_per_second": 81.826,
|
| 12927 |
"eval_steps_per_second": 0.639,
|
| 12928 |
"step": 1700000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12929 |
}
|
| 12930 |
],
|
| 12931 |
"max_steps": 2000000,
|
| 12932 |
"num_train_epochs": 9223372036854775807,
|
| 12933 |
-
"total_flos": 1.
|
| 12934 |
"trial_name": null,
|
| 12935 |
"trial_params": null
|
| 12936 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.125,
|
| 5 |
+
"global_step": 1750000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 12926 |
"eval_samples_per_second": 81.826,
|
| 12927 |
"eval_steps_per_second": 0.639,
|
| 12928 |
"step": 1700000
|
| 12929 |
+
},
|
| 12930 |
+
{
|
| 12931 |
+
"epoch": 0.1,
|
| 12932 |
+
"learning_rate": 1.9356303574345033e-05,
|
| 12933 |
+
"loss": 0.44,
|
| 12934 |
+
"step": 1701000
|
| 12935 |
+
},
|
| 12936 |
+
{
|
| 12937 |
+
"epoch": 0.1,
|
| 12938 |
+
"learning_rate": 1.9295375753654256e-05,
|
| 12939 |
+
"loss": 0.4406,
|
| 12940 |
+
"step": 1702000
|
| 12941 |
+
},
|
| 12942 |
+
{
|
| 12943 |
+
"epoch": 0.1,
|
| 12944 |
+
"learning_rate": 1.9234693500252896e-05,
|
| 12945 |
+
"loss": 0.4392,
|
| 12946 |
+
"step": 1703000
|
| 12947 |
+
},
|
| 12948 |
+
{
|
| 12949 |
+
"epoch": 0.1,
|
| 12950 |
+
"learning_rate": 1.9174195978495195e-05,
|
| 12951 |
+
"loss": 0.4389,
|
| 12952 |
+
"step": 1704000
|
| 12953 |
+
},
|
| 12954 |
+
{
|
| 12955 |
+
"epoch": 0.1,
|
| 12956 |
+
"learning_rate": 1.9113823092023844e-05,
|
| 12957 |
+
"loss": 0.4395,
|
| 12958 |
+
"step": 1705000
|
| 12959 |
+
},
|
| 12960 |
+
{
|
| 12961 |
+
"epoch": 0.1,
|
| 12962 |
+
"eval_loss": 0.42103949189186096,
|
| 12963 |
+
"eval_runtime": 79.7626,
|
| 12964 |
+
"eval_samples_per_second": 80.238,
|
| 12965 |
+
"eval_steps_per_second": 0.627,
|
| 12966 |
+
"step": 1705000
|
| 12967 |
+
},
|
| 12968 |
+
{
|
| 12969 |
+
"epoch": 0.1,
|
| 12970 |
+
"learning_rate": 1.9053635675406527e-05,
|
| 12971 |
+
"loss": 0.4387,
|
| 12972 |
+
"step": 1706000
|
| 12973 |
+
},
|
| 12974 |
+
{
|
| 12975 |
+
"epoch": 0.1,
|
| 12976 |
+
"learning_rate": 1.899363391198454e-05,
|
| 12977 |
+
"loss": 0.4405,
|
| 12978 |
+
"step": 1707000
|
| 12979 |
+
},
|
| 12980 |
+
{
|
| 12981 |
+
"epoch": 0.1,
|
| 12982 |
+
"learning_rate": 1.893381798453365e-05,
|
| 12983 |
+
"loss": 0.4395,
|
| 12984 |
+
"step": 1708000
|
| 12985 |
+
},
|
| 12986 |
+
{
|
| 12987 |
+
"epoch": 0.1,
|
| 12988 |
+
"learning_rate": 1.887418807526355e-05,
|
| 12989 |
+
"loss": 0.439,
|
| 12990 |
+
"step": 1709000
|
| 12991 |
+
},
|
| 12992 |
+
{
|
| 12993 |
+
"epoch": 0.1,
|
| 12994 |
+
"learning_rate": 1.8814803716459616e-05,
|
| 12995 |
+
"loss": 0.439,
|
| 12996 |
+
"step": 1710000
|
| 12997 |
+
},
|
| 12998 |
+
{
|
| 12999 |
+
"epoch": 0.1,
|
| 13000 |
+
"eval_loss": 0.42225512862205505,
|
| 13001 |
+
"eval_runtime": 77.1239,
|
| 13002 |
+
"eval_samples_per_second": 82.983,
|
| 13003 |
+
"eval_steps_per_second": 0.648,
|
| 13004 |
+
"step": 1710000
|
| 13005 |
+
},
|
| 13006 |
+
{
|
| 13007 |
+
"epoch": 0.11,
|
| 13008 |
+
"learning_rate": 1.875560536579964e-05,
|
| 13009 |
+
"loss": 0.439,
|
| 13010 |
+
"step": 1711000
|
| 13011 |
+
},
|
| 13012 |
+
{
|
| 13013 |
+
"epoch": 0.11,
|
| 13014 |
+
"learning_rate": 1.8696534225358292e-05,
|
| 13015 |
+
"loss": 0.4392,
|
| 13016 |
+
"step": 1712000
|
| 13017 |
+
},
|
| 13018 |
+
{
|
| 13019 |
+
"epoch": 0.11,
|
| 13020 |
+
"learning_rate": 1.8637708616967782e-05,
|
| 13021 |
+
"loss": 0.4397,
|
| 13022 |
+
"step": 1713000
|
| 13023 |
+
},
|
| 13024 |
+
{
|
| 13025 |
+
"epoch": 0.11,
|
| 13026 |
+
"learning_rate": 1.8579010950865316e-05,
|
| 13027 |
+
"loss": 0.4385,
|
| 13028 |
+
"step": 1714000
|
| 13029 |
+
},
|
| 13030 |
+
{
|
| 13031 |
+
"epoch": 0.11,
|
| 13032 |
+
"learning_rate": 1.852050038374741e-05,
|
| 13033 |
+
"loss": 0.4391,
|
| 13034 |
+
"step": 1715000
|
| 13035 |
+
},
|
| 13036 |
+
{
|
| 13037 |
+
"epoch": 0.11,
|
| 13038 |
+
"eval_loss": 0.420716792345047,
|
| 13039 |
+
"eval_runtime": 78.5003,
|
| 13040 |
+
"eval_samples_per_second": 81.528,
|
| 13041 |
+
"eval_steps_per_second": 0.637,
|
| 13042 |
+
"step": 1715000
|
| 13043 |
+
},
|
| 13044 |
+
{
|
| 13045 |
+
"epoch": 0.11,
|
| 13046 |
+
"learning_rate": 1.8462235323533128e-05,
|
| 13047 |
+
"loss": 0.4395,
|
| 13048 |
+
"step": 1716000
|
| 13049 |
+
},
|
| 13050 |
+
{
|
| 13051 |
+
"epoch": 0.11,
|
| 13052 |
+
"learning_rate": 1.8404099300970416e-05,
|
| 13053 |
+
"loss": 0.4378,
|
| 13054 |
+
"step": 1717000
|
| 13055 |
+
},
|
| 13056 |
+
{
|
| 13057 |
+
"epoch": 0.11,
|
| 13058 |
+
"learning_rate": 1.8346208764813356e-05,
|
| 13059 |
+
"loss": 0.4408,
|
| 13060 |
+
"step": 1718000
|
| 13061 |
+
},
|
| 13062 |
+
{
|
| 13063 |
+
"epoch": 0.11,
|
| 13064 |
+
"learning_rate": 1.8288447994466744e-05,
|
| 13065 |
+
"loss": 0.4388,
|
| 13066 |
+
"step": 1719000
|
| 13067 |
+
},
|
| 13068 |
+
{
|
| 13069 |
+
"epoch": 0.11,
|
| 13070 |
+
"learning_rate": 1.8230932687039617e-05,
|
| 13071 |
+
"loss": 0.439,
|
| 13072 |
+
"step": 1720000
|
| 13073 |
+
},
|
| 13074 |
+
{
|
| 13075 |
+
"epoch": 0.11,
|
| 13076 |
+
"eval_loss": 0.41757285594940186,
|
| 13077 |
+
"eval_runtime": 79.8473,
|
| 13078 |
+
"eval_samples_per_second": 80.153,
|
| 13079 |
+
"eval_steps_per_second": 0.626,
|
| 13080 |
+
"step": 1720000
|
| 13081 |
+
},
|
| 13082 |
+
{
|
| 13083 |
+
"epoch": 0.11,
|
| 13084 |
+
"learning_rate": 1.8173547872002242e-05,
|
| 13085 |
+
"loss": 0.4384,
|
| 13086 |
+
"step": 1721000
|
| 13087 |
+
},
|
| 13088 |
+
{
|
| 13089 |
+
"epoch": 0.11,
|
| 13090 |
+
"learning_rate": 1.811640849341029e-05,
|
| 13091 |
+
"loss": 0.4401,
|
| 13092 |
+
"step": 1722000
|
| 13093 |
+
},
|
| 13094 |
+
{
|
| 13095 |
+
"epoch": 0.11,
|
| 13096 |
+
"learning_rate": 1.8059400332198968e-05,
|
| 13097 |
+
"loss": 0.438,
|
| 13098 |
+
"step": 1723000
|
| 13099 |
+
},
|
| 13100 |
+
{
|
| 13101 |
+
"epoch": 0.11,
|
| 13102 |
+
"learning_rate": 1.8002580852796262e-05,
|
| 13103 |
+
"loss": 0.4401,
|
| 13104 |
+
"step": 1724000
|
| 13105 |
+
},
|
| 13106 |
+
{
|
| 13107 |
+
"epoch": 0.11,
|
| 13108 |
+
"learning_rate": 1.7945950228284155e-05,
|
| 13109 |
+
"loss": 0.4401,
|
| 13110 |
+
"step": 1725000
|
| 13111 |
+
},
|
| 13112 |
+
{
|
| 13113 |
+
"epoch": 0.11,
|
| 13114 |
+
"eval_loss": 0.41903457045555115,
|
| 13115 |
+
"eval_runtime": 77.4134,
|
| 13116 |
+
"eval_samples_per_second": 82.673,
|
| 13117 |
+
"eval_steps_per_second": 0.646,
|
| 13118 |
+
"step": 1725000
|
| 13119 |
+
},
|
| 13120 |
+
{
|
| 13121 |
+
"epoch": 0.11,
|
| 13122 |
+
"learning_rate": 1.788950863116934e-05,
|
| 13123 |
+
"loss": 0.4383,
|
| 13124 |
+
"step": 1726000
|
| 13125 |
+
},
|
| 13126 |
+
{
|
| 13127 |
+
"epoch": 0.11,
|
| 13128 |
+
"learning_rate": 1.783331239121836e-05,
|
| 13129 |
+
"loss": 0.4383,
|
| 13130 |
+
"step": 1727000
|
| 13131 |
+
},
|
| 13132 |
+
{
|
| 13133 |
+
"epoch": 0.11,
|
| 13134 |
+
"learning_rate": 1.7777305143227536e-05,
|
| 13135 |
+
"loss": 0.4401,
|
| 13136 |
+
"step": 1728000
|
| 13137 |
+
},
|
| 13138 |
+
{
|
| 13139 |
+
"epoch": 0.11,
|
| 13140 |
+
"learning_rate": 1.772143127833117e-05,
|
| 13141 |
+
"loss": 0.4391,
|
| 13142 |
+
"step": 1729000
|
| 13143 |
+
},
|
| 13144 |
+
{
|
| 13145 |
+
"epoch": 0.12,
|
| 13146 |
+
"learning_rate": 1.766574712475575e-05,
|
| 13147 |
+
"loss": 0.439,
|
| 13148 |
+
"step": 1730000
|
| 13149 |
+
},
|
| 13150 |
+
{
|
| 13151 |
+
"epoch": 0.12,
|
| 13152 |
+
"eval_loss": 0.4182310104370117,
|
| 13153 |
+
"eval_runtime": 75.5121,
|
| 13154 |
+
"eval_samples_per_second": 84.755,
|
| 13155 |
+
"eval_steps_per_second": 0.662,
|
| 13156 |
+
"step": 1730000
|
| 13157 |
+
},
|
| 13158 |
+
{
|
| 13159 |
+
"epoch": 0.12,
|
| 13160 |
+
"learning_rate": 1.7610252852124898e-05,
|
| 13161 |
+
"loss": 0.4387,
|
| 13162 |
+
"step": 1731000
|
| 13163 |
+
},
|
| 13164 |
+
{
|
| 13165 |
+
"epoch": 0.12,
|
| 13166 |
+
"learning_rate": 1.755494862948377e-05,
|
| 13167 |
+
"loss": 0.4382,
|
| 13168 |
+
"step": 1732000
|
| 13169 |
+
},
|
| 13170 |
+
{
|
| 13171 |
+
"epoch": 0.12,
|
| 13172 |
+
"learning_rate": 1.7499889644232756e-05,
|
| 13173 |
+
"loss": 0.4385,
|
| 13174 |
+
"step": 1733000
|
| 13175 |
+
},
|
| 13176 |
+
{
|
| 13177 |
+
"epoch": 0.12,
|
| 13178 |
+
"learning_rate": 1.744496583592041e-05,
|
| 13179 |
+
"loss": 0.4408,
|
| 13180 |
+
"step": 1734000
|
| 13181 |
+
},
|
| 13182 |
+
{
|
| 13183 |
+
"epoch": 0.12,
|
| 13184 |
+
"learning_rate": 1.7390287219108524e-05,
|
| 13185 |
+
"loss": 0.4401,
|
| 13186 |
+
"step": 1735000
|
| 13187 |
+
},
|
| 13188 |
+
{
|
| 13189 |
+
"epoch": 0.12,
|
| 13190 |
+
"eval_loss": 0.4186602830886841,
|
| 13191 |
+
"eval_runtime": 80.3977,
|
| 13192 |
+
"eval_samples_per_second": 79.604,
|
| 13193 |
+
"eval_steps_per_second": 0.622,
|
| 13194 |
+
"step": 1735000
|
| 13195 |
+
},
|
| 13196 |
+
{
|
| 13197 |
+
"epoch": 0.12,
|
| 13198 |
+
"learning_rate": 1.733574449368513e-05,
|
| 13199 |
+
"loss": 0.4391,
|
| 13200 |
+
"step": 1736000
|
| 13201 |
+
},
|
| 13202 |
+
{
|
| 13203 |
+
"epoch": 0.12,
|
| 13204 |
+
"learning_rate": 1.7281392654451555e-05,
|
| 13205 |
+
"loss": 0.4401,
|
| 13206 |
+
"step": 1737000
|
| 13207 |
+
},
|
| 13208 |
+
{
|
| 13209 |
+
"epoch": 0.12,
|
| 13210 |
+
"learning_rate": 1.7227339997768454e-05,
|
| 13211 |
+
"loss": 0.4405,
|
| 13212 |
+
"step": 1738000
|
| 13213 |
+
},
|
| 13214 |
+
{
|
| 13215 |
+
"epoch": 0.12,
|
| 13216 |
+
"learning_rate": 1.7173370044430122e-05,
|
| 13217 |
+
"loss": 0.439,
|
| 13218 |
+
"step": 1739000
|
| 13219 |
+
},
|
| 13220 |
+
{
|
| 13221 |
+
"epoch": 0.12,
|
| 13222 |
+
"learning_rate": 1.7119591471902336e-05,
|
| 13223 |
+
"loss": 0.4397,
|
| 13224 |
+
"step": 1740000
|
| 13225 |
+
},
|
| 13226 |
+
{
|
| 13227 |
+
"epoch": 0.12,
|
| 13228 |
+
"eval_loss": 0.41898131370544434,
|
| 13229 |
+
"eval_runtime": 77.8556,
|
| 13230 |
+
"eval_samples_per_second": 82.203,
|
| 13231 |
+
"eval_steps_per_second": 0.642,
|
| 13232 |
+
"step": 1740000
|
| 13233 |
+
},
|
| 13234 |
+
{
|
| 13235 |
+
"epoch": 0.12,
|
| 13236 |
+
"learning_rate": 1.7066004444003927e-05,
|
| 13237 |
+
"loss": 0.4388,
|
| 13238 |
+
"step": 1741000
|
| 13239 |
+
},
|
| 13240 |
+
{
|
| 13241 |
+
"epoch": 0.12,
|
| 13242 |
+
"learning_rate": 1.7012609123970294e-05,
|
| 13243 |
+
"loss": 0.4388,
|
| 13244 |
+
"step": 1742000
|
| 13245 |
+
},
|
| 13246 |
+
{
|
| 13247 |
+
"epoch": 0.12,
|
| 13248 |
+
"learning_rate": 1.6959405674452816e-05,
|
| 13249 |
+
"loss": 0.4393,
|
| 13250 |
+
"step": 1743000
|
| 13251 |
+
},
|
| 13252 |
+
{
|
| 13253 |
+
"epoch": 0.12,
|
| 13254 |
+
"learning_rate": 1.6906447172961322e-05,
|
| 13255 |
+
"loss": 0.4386,
|
| 13256 |
+
"step": 1744000
|
| 13257 |
+
},
|
| 13258 |
+
{
|
| 13259 |
+
"epoch": 0.12,
|
| 13260 |
+
"learning_rate": 1.6853627757817506e-05,
|
| 13261 |
+
"loss": 0.4379,
|
| 13262 |
+
"step": 1745000
|
| 13263 |
+
},
|
| 13264 |
+
{
|
| 13265 |
+
"epoch": 0.12,
|
| 13266 |
+
"eval_loss": 0.41874217987060547,
|
| 13267 |
+
"eval_runtime": 79.3439,
|
| 13268 |
+
"eval_samples_per_second": 80.662,
|
| 13269 |
+
"eval_steps_per_second": 0.63,
|
| 13270 |
+
"step": 1745000
|
| 13271 |
+
},
|
| 13272 |
+
{
|
| 13273 |
+
"epoch": 0.12,
|
| 13274 |
+
"learning_rate": 1.6801053228400387e-05,
|
| 13275 |
+
"loss": 0.4407,
|
| 13276 |
+
"step": 1746000
|
| 13277 |
+
},
|
| 13278 |
+
{
|
| 13279 |
+
"epoch": 0.12,
|
| 13280 |
+
"learning_rate": 1.6748618490574697e-05,
|
| 13281 |
+
"loss": 0.4398,
|
| 13282 |
+
"step": 1747000
|
| 13283 |
+
},
|
| 13284 |
+
{
|
| 13285 |
+
"epoch": 0.12,
|
| 13286 |
+
"learning_rate": 1.669637642742642e-05,
|
| 13287 |
+
"loss": 0.4385,
|
| 13288 |
+
"step": 1748000
|
| 13289 |
+
},
|
| 13290 |
+
{
|
| 13291 |
+
"epoch": 0.12,
|
| 13292 |
+
"learning_rate": 1.6644327198093962e-05,
|
| 13293 |
+
"loss": 0.4376,
|
| 13294 |
+
"step": 1749000
|
| 13295 |
+
},
|
| 13296 |
+
{
|
| 13297 |
+
"epoch": 0.12,
|
| 13298 |
+
"learning_rate": 1.6592522720912954e-05,
|
| 13299 |
+
"loss": 0.4381,
|
| 13300 |
+
"step": 1750000
|
| 13301 |
+
},
|
| 13302 |
+
{
|
| 13303 |
+
"epoch": 0.12,
|
| 13304 |
+
"eval_loss": 0.42223626375198364,
|
| 13305 |
+
"eval_runtime": 79.3599,
|
| 13306 |
+
"eval_samples_per_second": 80.645,
|
| 13307 |
+
"eval_steps_per_second": 0.63,
|
| 13308 |
+
"step": 1750000
|
| 13309 |
}
|
| 13310 |
],
|
| 13311 |
"max_steps": 2000000,
|
| 13312 |
"num_train_epochs": 9223372036854775807,
|
| 13313 |
+
"total_flos": 1.533443229351936e+22,
|
| 13314 |
"trial_name": null,
|
| 13315 |
"trial_params": null
|
| 13316 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4b2f64ee4b8a3f1cf3d86fb133d82c77bc0f7052c00d93cb35fb4180acc8509
|
| 3 |
size 449471589
|