Commit
•
024a457
1
Parent(s):
7f9042d
Training in progress, step 4500
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/generation_config.json +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Feb11_14-00-34_74e5e7b42358/1676124921.3277113/events.out.tfevents.1676124921.74e5e7b42358.292.1 +3 -0
- runs/Feb11_14-00-34_74e5e7b42358/events.out.tfevents.1676124921.74e5e7b42358.292.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"tokenizer_class": "T5Tokenizer",
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.26.
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 250112
|
| 36 |
}
|
|
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"tokenizer_class": "T5Tokenizer",
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.26.1",
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 250112
|
| 36 |
}
|
last-checkpoint/config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"tokenizer_class": "T5Tokenizer",
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
-
"transformers_version": "4.26.
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 250112
|
| 36 |
}
|
|
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"tokenizer_class": "T5Tokenizer",
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.26.1",
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 250112
|
| 36 |
}
|
last-checkpoint/generation_config.json
CHANGED
|
@@ -7,5 +7,5 @@
|
|
| 7 |
"no_repeat_ngram_size": 2,
|
| 8 |
"num_beams": 15,
|
| 9 |
"pad_token_id": 0,
|
| 10 |
-
"transformers_version": "4.26.
|
| 11 |
}
|
|
|
|
| 7 |
"no_repeat_ngram_size": 2,
|
| 8 |
"num_beams": 15,
|
| 9 |
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "4.26.1"
|
| 11 |
}
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979fae33b211827802e243d4b2113809f0f0cecb9b7c1d248e072e2b037b2cb0
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f4336db612efb7d62e5471628f98da8a89b2945716dfd11cbdd02c45bd395f
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c4dc079a6baea2794599f0f64419cf3494f7a5dbc363ce3a63466ab6608372
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eea54d69309341d06e47639645523531f831191f588becdb9503cc4509f35e8f
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2886,11 +2886,371 @@
|
|
| 2886 |
"eval_samples_per_second": 0.22,
|
| 2887 |
"eval_steps_per_second": 0.22,
|
| 2888 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2889 |
}
|
| 2890 |
],
|
| 2891 |
"max_steps": 5060,
|
| 2892 |
"num_train_epochs": 10,
|
| 2893 |
-
"total_flos":
|
| 2894 |
"trial_name": null,
|
| 2895 |
"trial_params": null
|
| 2896 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.891628652447293,
|
| 5 |
+
"global_step": 4500,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2886 |
"eval_samples_per_second": 0.22,
|
| 2887 |
"eval_steps_per_second": 0.22,
|
| 2888 |
"step": 4000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 7.92,
|
| 2892 |
+
"learning_rate": 0.00010563380281690141,
|
| 2893 |
+
"loss": 0.1264,
|
| 2894 |
+
"step": 4010
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 7.94,
|
| 2898 |
+
"learning_rate": 0.00010462776659959759,
|
| 2899 |
+
"loss": 0.1026,
|
| 2900 |
+
"step": 4020
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 7.96,
|
| 2904 |
+
"learning_rate": 0.00010362173038229377,
|
| 2905 |
+
"loss": 0.1348,
|
| 2906 |
+
"step": 4030
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 7.98,
|
| 2910 |
+
"learning_rate": 0.00010261569416498995,
|
| 2911 |
+
"loss": 0.1893,
|
| 2912 |
+
"step": 4040
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 8.0,
|
| 2916 |
+
"learning_rate": 0.00010160965794768612,
|
| 2917 |
+
"loss": 0.1048,
|
| 2918 |
+
"step": 4050
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 8.02,
|
| 2922 |
+
"learning_rate": 0.0001006036217303823,
|
| 2923 |
+
"loss": 0.1576,
|
| 2924 |
+
"step": 4060
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 8.04,
|
| 2928 |
+
"learning_rate": 9.959758551307847e-05,
|
| 2929 |
+
"loss": 0.1084,
|
| 2930 |
+
"step": 4070
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 8.06,
|
| 2934 |
+
"learning_rate": 9.859154929577464e-05,
|
| 2935 |
+
"loss": 0.089,
|
| 2936 |
+
"step": 4080
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 8.08,
|
| 2940 |
+
"learning_rate": 9.758551307847083e-05,
|
| 2941 |
+
"loss": 0.0989,
|
| 2942 |
+
"step": 4090
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 8.1,
|
| 2946 |
+
"learning_rate": 9.6579476861167e-05,
|
| 2947 |
+
"loss": 0.108,
|
| 2948 |
+
"step": 4100
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 8.1,
|
| 2952 |
+
"eval_loss": 0.9726575016975403,
|
| 2953 |
+
"eval_rouge1": 0.1383333333333333,
|
| 2954 |
+
"eval_rouge2": 0.10340909090909092,
|
| 2955 |
+
"eval_rougeL": 0.14448717948717948,
|
| 2956 |
+
"eval_rougeLsum": 0.13666666666666666,
|
| 2957 |
+
"eval_runtime": 89.426,
|
| 2958 |
+
"eval_samples_per_second": 0.224,
|
| 2959 |
+
"eval_steps_per_second": 0.224,
|
| 2960 |
+
"step": 4100
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 8.12,
|
| 2964 |
+
"learning_rate": 9.557344064386318e-05,
|
| 2965 |
+
"loss": 0.0576,
|
| 2966 |
+
"step": 4110
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 8.14,
|
| 2970 |
+
"learning_rate": 9.456740442655936e-05,
|
| 2971 |
+
"loss": 0.0937,
|
| 2972 |
+
"step": 4120
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 8.16,
|
| 2976 |
+
"learning_rate": 9.356136820925553e-05,
|
| 2977 |
+
"loss": 0.0814,
|
| 2978 |
+
"step": 4130
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 8.18,
|
| 2982 |
+
"learning_rate": 9.255533199195171e-05,
|
| 2983 |
+
"loss": 0.0832,
|
| 2984 |
+
"step": 4140
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 8.2,
|
| 2988 |
+
"learning_rate": 9.15492957746479e-05,
|
| 2989 |
+
"loss": 0.0881,
|
| 2990 |
+
"step": 4150
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 8.22,
|
| 2994 |
+
"learning_rate": 9.054325955734406e-05,
|
| 2995 |
+
"loss": 0.0785,
|
| 2996 |
+
"step": 4160
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 8.24,
|
| 3000 |
+
"learning_rate": 8.953722334004025e-05,
|
| 3001 |
+
"loss": 0.1046,
|
| 3002 |
+
"step": 4170
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 8.26,
|
| 3006 |
+
"learning_rate": 8.853118712273642e-05,
|
| 3007 |
+
"loss": 0.1137,
|
| 3008 |
+
"step": 4180
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 8.28,
|
| 3012 |
+
"learning_rate": 8.75251509054326e-05,
|
| 3013 |
+
"loss": 0.0966,
|
| 3014 |
+
"step": 4190
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 8.3,
|
| 3018 |
+
"learning_rate": 8.651911468812877e-05,
|
| 3019 |
+
"loss": 0.1292,
|
| 3020 |
+
"step": 4200
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 8.3,
|
| 3024 |
+
"eval_loss": 0.9639500379562378,
|
| 3025 |
+
"eval_rouge1": 0.21000000000000002,
|
| 3026 |
+
"eval_rouge2": 0.12563131313131312,
|
| 3027 |
+
"eval_rougeL": 0.2097902097902098,
|
| 3028 |
+
"eval_rougeLsum": 0.20979020979020976,
|
| 3029 |
+
"eval_runtime": 86.8779,
|
| 3030 |
+
"eval_samples_per_second": 0.23,
|
| 3031 |
+
"eval_steps_per_second": 0.23,
|
| 3032 |
+
"step": 4200
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 8.32,
|
| 3036 |
+
"learning_rate": 8.551307847082495e-05,
|
| 3037 |
+
"loss": 0.099,
|
| 3038 |
+
"step": 4210
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 8.34,
|
| 3042 |
+
"learning_rate": 8.450704225352113e-05,
|
| 3043 |
+
"loss": 0.082,
|
| 3044 |
+
"step": 4220
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 8.36,
|
| 3048 |
+
"learning_rate": 8.350100603621731e-05,
|
| 3049 |
+
"loss": 0.1007,
|
| 3050 |
+
"step": 4230
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 8.38,
|
| 3054 |
+
"learning_rate": 8.249496981891348e-05,
|
| 3055 |
+
"loss": 0.0826,
|
| 3056 |
+
"step": 4240
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 8.4,
|
| 3060 |
+
"learning_rate": 8.148893360160967e-05,
|
| 3061 |
+
"loss": 0.0823,
|
| 3062 |
+
"step": 4250
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 8.42,
|
| 3066 |
+
"learning_rate": 8.048289738430584e-05,
|
| 3067 |
+
"loss": 0.0863,
|
| 3068 |
+
"step": 4260
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 8.44,
|
| 3072 |
+
"learning_rate": 7.9476861167002e-05,
|
| 3073 |
+
"loss": 0.1037,
|
| 3074 |
+
"step": 4270
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 8.46,
|
| 3078 |
+
"learning_rate": 7.847082494969819e-05,
|
| 3079 |
+
"loss": 0.097,
|
| 3080 |
+
"step": 4280
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 8.48,
|
| 3084 |
+
"learning_rate": 7.746478873239437e-05,
|
| 3085 |
+
"loss": 0.0589,
|
| 3086 |
+
"step": 4290
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 8.5,
|
| 3090 |
+
"learning_rate": 7.645875251509054e-05,
|
| 3091 |
+
"loss": 0.0868,
|
| 3092 |
+
"step": 4300
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 8.5,
|
| 3096 |
+
"eval_loss": 0.9618169069290161,
|
| 3097 |
+
"eval_rouge1": 0.15,
|
| 3098 |
+
"eval_rouge2": 0.09431818181818181,
|
| 3099 |
+
"eval_rougeL": 0.15076923076923077,
|
| 3100 |
+
"eval_rougeLsum": 0.1465384615384615,
|
| 3101 |
+
"eval_runtime": 86.2134,
|
| 3102 |
+
"eval_samples_per_second": 0.232,
|
| 3103 |
+
"eval_steps_per_second": 0.232,
|
| 3104 |
+
"step": 4300
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 8.52,
|
| 3108 |
+
"learning_rate": 7.545271629778672e-05,
|
| 3109 |
+
"loss": 0.0964,
|
| 3110 |
+
"step": 4310
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 8.54,
|
| 3114 |
+
"learning_rate": 7.444668008048291e-05,
|
| 3115 |
+
"loss": 0.1144,
|
| 3116 |
+
"step": 4320
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 8.56,
|
| 3120 |
+
"learning_rate": 7.344064386317907e-05,
|
| 3121 |
+
"loss": 0.1029,
|
| 3122 |
+
"step": 4330
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 8.58,
|
| 3126 |
+
"learning_rate": 7.243460764587526e-05,
|
| 3127 |
+
"loss": 0.0978,
|
| 3128 |
+
"step": 4340
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 8.6,
|
| 3132 |
+
"learning_rate": 7.142857142857142e-05,
|
| 3133 |
+
"loss": 0.142,
|
| 3134 |
+
"step": 4350
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 8.62,
|
| 3138 |
+
"learning_rate": 7.042253521126761e-05,
|
| 3139 |
+
"loss": 0.0957,
|
| 3140 |
+
"step": 4360
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 8.64,
|
| 3144 |
+
"learning_rate": 6.941649899396378e-05,
|
| 3145 |
+
"loss": 0.0896,
|
| 3146 |
+
"step": 4370
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 8.65,
|
| 3150 |
+
"learning_rate": 6.841046277665996e-05,
|
| 3151 |
+
"loss": 0.0998,
|
| 3152 |
+
"step": 4380
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 8.67,
|
| 3156 |
+
"learning_rate": 6.740442655935614e-05,
|
| 3157 |
+
"loss": 0.0828,
|
| 3158 |
+
"step": 4390
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 8.69,
|
| 3162 |
+
"learning_rate": 6.639839034205232e-05,
|
| 3163 |
+
"loss": 0.1023,
|
| 3164 |
+
"step": 4400
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 8.69,
|
| 3168 |
+
"eval_loss": 0.9609012603759766,
|
| 3169 |
+
"eval_rouge1": 0.18,
|
| 3170 |
+
"eval_rouge2": 0.075,
|
| 3171 |
+
"eval_rougeL": 0.18,
|
| 3172 |
+
"eval_rougeLsum": 0.18,
|
| 3173 |
+
"eval_runtime": 85.733,
|
| 3174 |
+
"eval_samples_per_second": 0.233,
|
| 3175 |
+
"eval_steps_per_second": 0.233,
|
| 3176 |
+
"step": 4400
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 8.71,
|
| 3180 |
+
"learning_rate": 6.539235412474849e-05,
|
| 3181 |
+
"loss": 0.1324,
|
| 3182 |
+
"step": 4410
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 8.73,
|
| 3186 |
+
"learning_rate": 6.438631790744468e-05,
|
| 3187 |
+
"loss": 0.1107,
|
| 3188 |
+
"step": 4420
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 8.75,
|
| 3192 |
+
"learning_rate": 6.338028169014085e-05,
|
| 3193 |
+
"loss": 0.0756,
|
| 3194 |
+
"step": 4430
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 8.77,
|
| 3198 |
+
"learning_rate": 6.237424547283703e-05,
|
| 3199 |
+
"loss": 0.1019,
|
| 3200 |
+
"step": 4440
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 8.79,
|
| 3204 |
+
"learning_rate": 6.13682092555332e-05,
|
| 3205 |
+
"loss": 0.1232,
|
| 3206 |
+
"step": 4450
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 8.81,
|
| 3210 |
+
"learning_rate": 6.036217303822938e-05,
|
| 3211 |
+
"loss": 0.1186,
|
| 3212 |
+
"step": 4460
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 8.83,
|
| 3216 |
+
"learning_rate": 5.935613682092555e-05,
|
| 3217 |
+
"loss": 0.1093,
|
| 3218 |
+
"step": 4470
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 8.85,
|
| 3222 |
+
"learning_rate": 5.8350100603621735e-05,
|
| 3223 |
+
"loss": 0.1009,
|
| 3224 |
+
"step": 4480
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 8.87,
|
| 3228 |
+
"learning_rate": 5.734406438631791e-05,
|
| 3229 |
+
"loss": 0.0878,
|
| 3230 |
+
"step": 4490
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 8.89,
|
| 3234 |
+
"learning_rate": 5.6338028169014086e-05,
|
| 3235 |
+
"loss": 0.1102,
|
| 3236 |
+
"step": 4500
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 8.89,
|
| 3240 |
+
"eval_loss": 0.9644363522529602,
|
| 3241 |
+
"eval_rouge1": 0.14615384615384613,
|
| 3242 |
+
"eval_rouge2": 0.1,
|
| 3243 |
+
"eval_rougeL": 0.15115384615384614,
|
| 3244 |
+
"eval_rougeLsum": 0.145,
|
| 3245 |
+
"eval_runtime": 83.9759,
|
| 3246 |
+
"eval_samples_per_second": 0.238,
|
| 3247 |
+
"eval_steps_per_second": 0.238,
|
| 3248 |
+
"step": 4500
|
| 3249 |
}
|
| 3250 |
],
|
| 3251 |
"max_steps": 5060,
|
| 3252 |
"num_train_epochs": 10,
|
| 3253 |
+
"total_flos": 1.0952350126776115e+17,
|
| 3254 |
"trial_name": null,
|
| 3255 |
"trial_params": null
|
| 3256 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77a4f7038b50ddc31edcc81a5b698eebafae24d0db54d6acae4be1a9f931706a
|
| 3 |
size 3643
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f4336db612efb7d62e5471628f98da8a89b2945716dfd11cbdd02c45bd395f
|
| 3 |
size 2329702453
|
runs/Feb11_14-00-34_74e5e7b42358/1676124921.3277113/events.out.tfevents.1676124921.74e5e7b42358.292.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd4d2a0362ea25dd375e16ee87a5e18c502572377dceecc7cd828dda97eea7c9
|
| 3 |
+
size 5952
|
runs/Feb11_14-00-34_74e5e7b42358/events.out.tfevents.1676124921.74e5e7b42358.292.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e58a04a0e477b9d2ba2e1e319284b1a33bbd6d6814f990542656072fb5f45d84
|
| 3 |
+
size 14428
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77a4f7038b50ddc31edcc81a5b698eebafae24d0db54d6acae4be1a9f931706a
|
| 3 |
size 3643
|