End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.051597148180007935,
+    "eval_runtime": 3.1643,
+    "eval_samples_per_second": 1.264,
+    "eval_steps_per_second": 0.316,
+    "test_loss": 1.4216160774230957,
+    "test_runtime": 2.9307,
+    "test_samples_per_second": 1.365,
+    "test_steps_per_second": 0.341,
+    "total_flos": 1163339959320.0,
+    "train_loss": 0.13540960324462503,
+    "train_runtime": 98.8611,
+    "train_samples_per_second": 0.202,
+    "train_steps_per_second": 0.02
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.051597148180007935,
+    "eval_runtime": 3.1643,
+    "eval_samples_per_second": 1.264,
+    "eval_steps_per_second": 0.316
+}

runs/May08_20-21-08_2e4200763c33/events.out.tfevents.1715199904.2e4200763c33.30318.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012031204e6304aef5a9ae480b1a6b109080d86111dff894fa66575dde784764
+size 354

test_results.json

@@ -0,0 +1,6 @@
+{
+    "test_loss": 1.4216160774230957,
+    "test_runtime": 2.9307,
+    "test_samples_per_second": 1.365,
+    "test_steps_per_second": 0.341
+}

tokenizer.json

@@ -1,8 +1,15 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 77,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 77
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 49407,

tokenizer_config.json

@@ -23,9 +23,16 @@
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "max_length": null,
   "model_max_length": 77,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "processor_class": "CLIPProcessor",
+  "stride": 0,
   "tokenizer_class": "CLIPTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1163339959320.0,
+    "train_loss": 0.13540960324462503,
+    "train_runtime": 98.8611,
+    "train_samples_per_second": 0.202,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 1.0,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.9807307720184326,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0021,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.00024110873346216977,
+      "eval_runtime": 2.8556,
+      "eval_samples_per_second": 1.401,
+      "eval_steps_per_second": 0.35,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 147.52401733398438,
+      "learning_rate": 0.0,
+      "loss": 0.2687,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.051597148180007935,
+      "eval_runtime": 1.127,
+      "eval_samples_per_second": 3.549,
+      "eval_steps_per_second": 0.887,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "step": 2,
+      "total_flos": 1163339959320.0,
+      "train_loss": 0.13540960324462503,
+      "train_runtime": 98.8611,
+      "train_samples_per_second": 0.202,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1163339959320.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}