Training in progress, epoch 1, checkpoint

last-checkpoint/README.md

@@ -18,6 +18,7 @@ base_model: ybelkada/flan-t5-xl-sharded-bf16
 
 
 - **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 [More Information Needed]
 

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0901ef4c72c814db14a3115b33443c0f271b8bc59368f74ce5bea847fad02c3a
+oid sha256:22839e91238bac11b011018251c238f9e63c0e492b0fada32ad6a69326a8166b
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b1c5eeaa99a7f86b77343f798cfd9507836fa64d65e82bb21f83095b5d731a
+oid sha256:3b2c763ae1e53f9c843655098a974d0cedff73a5d78d191c64d35e57804c5a1e
 size 75667834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a9602385bd251ab8a08ac433c5b25c601bfae70b76d081617a93e73aa8a31e
+oid sha256:5d699a3534ad9a405df924f05f343e172daf40775115cf8668b11b075338e087
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f89f68aeb61c0c2820c13b93e00ef18a596c108c2a0da01c4ad0f7216416f47
+oid sha256:192b658bbc5565c6d56293ca6388f1d6c7d63ed7417fdbcdf3fd5d237d08974b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,44 +1,25 @@
 {
-  "best_metric": 0.11245250701904297,
-  "best_model_checkpoint": "devvanshhh/flanT5-xl-3/checkpoint-724",
-  "epoch": 2.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 724,
+  "global_step": 362,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_gen_len": 15.0,
-      "eval_loss": 3.7217626571655273,
-      "eval_rouge1": 2.4388,
-      "eval_rouge2": 1.5752,
-      "eval_rougeL": 2.1263,
-      "eval_rougeLsum": 2.1465,
-      "eval_runtime": 433.9672,
-      "eval_samples_per_second": 0.742,
-      "eval_steps_per_second": 0.094,
+      "eval_gen_len": 11.03416149068323,
+      "eval_loss": 5.1172404289245605,
+      "eval_rouge1": 29.4208,
+      "eval_rouge2": 23.1422,
+      "eval_rougeL": 26.8934,
+      "eval_rougeLsum": 26.9815,
+      "eval_runtime": 174.0267,
+      "eval_samples_per_second": 1.85,
+      "eval_steps_per_second": 0.236,
       "step": 362
-    },
-    {
-      "epoch": 1.38,
-      "learning_rate": 3e-05,
-      "loss": 23.0243,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_gen_len": 10.475155279503106,
-      "eval_loss": 0.11245250701904297,
-      "eval_rouge1": 4.5102,
-      "eval_rouge2": 3.4625,
-      "eval_rougeL": 4.0876,
-      "eval_rougeLsum": 4.1156,
-      "eval_runtime": 419.9548,
-      "eval_samples_per_second": 0.767,
-      "eval_steps_per_second": 0.098,
-      "step": 724
     }
   ],
   "logging_steps": 500,
@@ -46,7 +27,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4.970292961502822e+16,
+  "total_flos": 1941520688087040.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906aea18dfda56baec007bea80cbc060cea2f50e3717a40fd0629884832e57cd
+oid sha256:cc7c7dfaefbc7d97a69d8d21e66f9b856138e64a49a2e2bcbfa653fe637f4a66
 size 4856